© 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-3-1B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 1402
    Prev
    Next
    INDEX
    Explanations

    code comments and placeholders

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-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
    NaN
    0.66
    oteric
    0.65
    pielt
    0.63
    **,
    0.61
    ,”
    0.60
    Tube
    0.60
    Scr
    0.60
    AllWindows
    0.60
     सब्जेक्ट
    0.59
    <start_of_image>
    0.59
    POSITIVE LOGITS
     This
    1.25
     Это
    1.23
     TODO
    1.22
     यह
    1.22
     Despite
    1.20
     For
    1.20
     It
    1.18
     Moreover
    1.17
     Since
    1.15
     FIXME
    1.15
    Activations Density 0.145%

    No Known Activations