© 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. 300
    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
    -
    0.75
    0.73
     on
    0.71
     a
    0.67
     people
    0.64
     all
    0.63
    ,
    0.61
    .
    0.61
     in
    0.58
     (
    0.58
    POSITIVE LOGITS
    𒀌
    1.49
     debugDocument
    1.48
    𒁯
    1.48
    <unused1433>
    1.48
    <unused1500>
    1.47
    𒄖
    1.47
    TGFuZ
    1.47
    𒀹
    1.47
     ہُما
    1.47
     Pusenkoff
    1.47
    Activations Density 0.217%

    No Known Activations