© 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. 13-GEMMASCOPE-2-RES-16K
    7. 1883
    Prev
    Next
    INDEX
    Explanations

    Identifying section titles

    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_13_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
    <unused389>
    1.12
     %><%=
    1.10
    <unused1964>
    1.07
    <unused1900>
    1.06
    𐰆
    1.06
    <unused2155>
    1.03
    𐰞
    1.02
    <unused391>
    1.02
    <unused621>
    1.01
    𒀜
    1.01
    POSITIVE LOGITS
    ↵↵
    1.12
     Revised
    1.01
     -
    0.95
     Re
    0.93
     /
    0.90
     Enhancement
    0.88
    Revised
    0.87
     St
    0.86
     Review
    0.83
     Edition
    0.82
    Activations Density 0.428%

    No Known Activations