© 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. 1769
    Prev
    Next
    INDEX
    Explanations

    post title/description

    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
     device
    0.56
     ion
    0.56
     devices
    0.55
     treble
    0.53
     dramas
    0.52
     mill
    0.52
    ნ
    0.52
     could
    0.52
     bass
    0.52
    ร
    0.51
    POSITIVE LOGITS
    これは
    0.64
     Dieser
    0.63
     Tämä
    0.59
    Calculating
    0.58
    This
    0.57
     Personen
    0.57
    чис
    0.56
    ኔታ
    0.56
     Estimated
    0.56
    最初の
    0.55
    Activations Density 0.001%

    No Known Activations