© 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-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 8934
    Prev
    Next
    INDEX
    Explanations

    comma separated lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lasting
    0.55
    reached
    0.55
    ように
    0.53
    atchewan
    0.51
    niak
    0.51
    %、
    0.51
    ψει
    0.51
    <h5>
    0.49
    ENTIAL
    0.47
    iktok
    0.47
    POSITIVE LOGITS
     nouns
    0.60
    ージ
    0.57
     comulti
    0.57
     diuretics
    0.56
    彧
    0.56
     priests
    0.56
     crist
    0.55
    ̐
    0.55
     endorse
    0.54
     गेंदों
    0.54
    Activations Density 0.153%

    No Known Activations