© 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. 24-GEMMASCOPE-2-RES-16K
    7. 15177
    Prev
    Next
    INDEX
    Explanations

    comparing adjacent

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

    The neuron activates on numeric tokens or sequences (e.g. phone numbers, codes, or other multi‐digit numbers).

    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_24_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
    er
    0.85
    skins
    0.82
     whiche
    0.80
     sportsbook
    0.79
    ר
    0.79
    udarstvennyj
    0.77
    ಶ್ಚ
    0.75
    ﯼ
    0.75
    binoculars
    0.73
    leqslant
    0.71
    POSITIVE LOGITS
    蹄
    0.81
    دى
    0.77
    ع
    0.75
     Estes
    0.73
    ções
    0.73
    í
    0.72
    osin
    0.71
    iring
    0.70
     domínio
    0.70
     الأح
    0.68
    Activations Density 0.000%

    No Known Activations