© 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. 105901
    Prev
    Next
    INDEX
    Explanations

    identity, accounts, locate

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

    college admissions

    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
     perifer
    0.46
     paziente
    0.46
     centrale
    0.45
    塘
    0.45
    窿
    0.45
     littoral
    0.44
    थुरा
    0.44
    উল্লেখ
    0.43
    当中
    0.42
    గల
    0.42
    POSITIVE LOGITS
    z
    0.51
    uito
    0.50
    bungen
    0.50
    serialized
    0.50
    ob
    0.48
    jav
    0.46
    verified
    0.46
    yg
    0.45
     обна
    0.45
     Особенно
    0.44
    Activations Density 0.002%

    No Known Activations