Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 1686
    Prev
    Next
    INDEX
    Explanations

    code snippets and variable names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_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
    氢
    0.35
    thisTrack
    0.34
     BLAST
    0.33
    衄
    0.33
     простран
    0.33
    ^{+}(
    0.33
    郯
    0.32
    黝
    0.31
    embryon
    0.31
    ítom
    0.31
    POSITIVE LOGITS
     selected
    0.37
     chosen
    0.37
     and
    0.36
    ,
    0.35
     each
    0.34
    [],
    0.34
     specified
    0.33
     identified
    0.33
    _
    0.33
    name
    0.33
    Activations Density 0.374%

    No Known Activations