© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 1732
    Prev
    Next
    INDEX
    Explanations

    chill

    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_7_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
    และ
    2.11
    and
    1.97
    wa
    1.81
    And
    1.71
    enn
    1.67
    all
    1.66
    k
    1.65
    ku
    1.65
    '
    1.63
    s
    1.62
    POSITIVE LOGITS
    BibitemOpen
    2.19
     birthplace
    2.11
    ꘏
    2.11
    𐰆
    2.08
     домаћин
    2.00
     sông
    1.96
    ExpNow
    1.95
     身
    1.94
     modalCard
    1.93
     displaced
    1.91
    Activations Density 0.029%

    No Known Activations