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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 9394
    Prev
    Next
    INDEX
    Explanations

    contractions and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_17_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
    <unused566>
    1.06
     Announces
    1.06
    <unused2152>
    1.05
     tirelessly
    1.04
    <unused676>
    1.04
    <unused942>
    1.03
     Says
    1.03
    <unused2217>
    1.03
     Özellikle
    1.02
    <unused1066>
    1.02
    POSITIVE LOGITS
     =
    0.87
    =
    0.77
    ,
    0.74
    overline
    0.72
    ;
    0.70
    с
    0.69
    integer
    0.63
    centroid
    0.63
    incomplete
    0.62
    Gaussian
    0.62
    Activations Density 1.015%

    No Known Activations