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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 7440
    Prev
    Next
    INDEX
    Explanations

    Michelin starred, mock, SDA, Rational

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

    The neuron detects numeric values resembling geographic coordinates or dateline markers (i.e., the floating‐point numbers in parentheses following a location).

    oai_token-act-pair · o4-miniTriggered 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
    𝓼
    0.62
     якщо
    0.62
     गुर्जर
    0.61
    Якщо
    0.60
    ꞎ
    0.57
    ък
    0.55
     Якщо
    0.55
    ρθρο
    0.54
    ２
    0.54
    Ӯ
    0.53
    POSITIVE LOGITS
     اسمها
    0.54
     course
    0.53
     pew
    0.52
    AFP
    0.51
     instrumentality
    0.51
     mess
    0.50
     હોય
    0.50
     incarnation
    0.50
    Reuters
    0.50
    ναν
    0.49
    Activations Density 0.031%

    No Known Activations