© 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. 159600
    Prev
    Next
    INDEX
    Explanations

    infamous Santa, Life Art

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

    purpose, action, or consequence

    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
     প্রবণ
    0.48
    тивные
    0.46
    斬
    0.46
     अनुमोदन
    0.46
     cầm
    0.44
    рс
    0.43
     вследствие
    0.43
     pouches
    0.42
    幹
    0.42
     ambition
    0.42
    POSITIVE LOGITS
    Jesse
    0.49
     Jesse
    0.47
    Hari
    0.46
     putra
    0.46
     señaló
    0.45
    ATE
    0.44
    Mir
    0.44
    ază
    0.44
    に入れ
    0.44
     vám
    0.43
    Activations Density 0.000%

    No Known Activations