© 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
    5. 17-GEMMASCOPE-2-RES-16K
    7. 374
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_17_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <unused2172>
    1.02
    <unused2138>
    1.01
    <unused2164>
    0.96
    <unused2125>
    0.93
    <unused2130>
    0.93
     impairments
    0.86
     etcétera
    0.86
    <unused2153>
    0.84
    <unused2158>
    0.82
     darn
    0.82
    POSITIVE LOGITS
    ,
    3.54
    ،
    3.02
     ,
    2.94
    ,(
    2.89
    ，
    2.80
    ,#
    2.80
    ,/*
    2.75
    ,//
    2.73
    ,[
    2.72
     ،
    2.71
    Activations Density 0.425%

    No Known Activations