© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 11963
    Prev
    Next
    INDEX
    Explanations

    categorization by level popularity effort

    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
    setPreferred
    2.73
    endsWith
    2.71
    setVisible
    2.60
    atosis
    2.52
     краёва
    2.49
    束
    2.48
    енера
    2.42
    ྥ
    2.40
    settes
    2.38
    绅
    2.36
    POSITIVE LOGITS
    vine
    2.39
     Sau
    2.23
     sau
    2.22
     skala
    2.22
     skoro
    2.18
    ʤ
    2.16
    ƌ
    2.14
    stone
    2.09
     الاخر
    2.05
    ev
    2.05
    Activations Density 0.020%

    No Known Activations