© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 27809
    Prev
    Next
    INDEX
    Explanations

    upon [him/her/self/it]

    np_acts-logits-general · gemini-2.5-flash-lite

    start of action

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
    ن
    1.46
    ン
    1.20
    न
    0.96
    가
    0.95
    لي
    0.86
    的な
    0.85
    が
    0.84
     BEEN
    0.83
    د
    0.81
     Theres
    0.77
    POSITIVE LOGITS
    are
    1.25
    ate
    1.03
    <0x0D>
    1.00
    us
    0.98
    one
    0.98
    ing
    0.97
    ol
    0.96
    is
    0.94
    u
    0.94
    ato
    0.88
    Activations Density 0.324%

    No Known Activations