© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 2168
    Prev
    Next
    INDEX
    Explanations

    j.a.r.v.i.s. or s.m.a.r.t

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

    The neuron fires strongly on isolated uppercase letters and periods—i.e. individual initials and the punctuation of abbreviations.

    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
    .
    0.78
    。
    0.74
    ..
    0.70
    netlify
    0.65
    Item
    0.63
    ...
    0.63
    Type
    0.63
    在这种
    0.62
    ().
    0.61
    og
    0.61
    POSITIVE LOGITS
    ޔ
    0.72
    I
    0.70
     antiguas
    0.66
    J
    0.66
    S
    0.66
    E
    0.65
    എസ്
    0.64
    C
    0.64
     เกี่ยว
    0.62
     მხოლოდ
    0.62
    Activations Density 0.799%

    No Known Activations