© 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. 13-GEMMASCOPE-2-RES-16K
    7. 9190
    Prev
    Next
    INDEX
    Explanations

    this dude

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_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
    /
    1.17
    -
    1.11
    cas
    1.10
    :
    1.10
    iniai
    1.09
    CA
    1.02
     —
    1.01
    に関連
    1.00
    c
    1.00
     Terms
    0.99
    POSITIVE LOGITS
     militant
    1.73
     witty
    1.69
     communist
    1.69
     luscious
    1.60
     ingenious
    1.58
     socialist
    1.54
     sullen
    1.54
     peasant
    1.52
     mighty
    1.47
     nutritious
    1.46
    Activations Density 0.110%

    No Known Activations