© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 15790
    Prev
    Next
    INDEX
    Explanations

    snapped off

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron strongly activates on numeric tokens—especially measurements or statistics (e.g. decimal-point values, ping times, data sizes).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    numeric digits, particularly in sequences or lists of numbers.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    technical/computing jargon and standalone numerals, especially within system/network output or specifications

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Collins
    0.59
    Seminar
    0.57
    prepare
    0.55
    RouterModule
    0.54
    Compiler
    0.54
     円
    0.52
    Circular
    0.52
    royal
    0.51
    kq
    0.51
    FICATION
    0.50
    POSITIVE LOGITS
     포인트
    0.69
     infliction
    0.63
     Isaiah
    0.61
     SOLUTIONS
    0.61
    트는
    0.59
     좌표
    0.58
    طة
    0.57
     pyrr
    0.57
     ਇ
    0.56
    يمة
    0.55
    Activations Density 0.000%

    No Known Activations