© 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. 645
    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
     comprises
    0.97
     tiered
    0.94
    -,
    0.93
     striving
    0.92
     routinely
    0.92
     delivered
    0.91
     mechanically
    0.90
     presumption
    0.89
     witnessed
    0.89
     entering
    0.88
    POSITIVE LOGITS
    (
    1.65
    ((
    1.59
    (((
    1.47
    (*(
    1.33
    ([
    1.31
    ($(
    1.29
    (#
    1.28
    ((*
    1.23
    ("@
    1.22
    (&
    1.22
    Activations Density 0.218%

    No Known Activations