© 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. 229119
    Prev
    Next
    INDEX
    Explanations

    store, $, integrated, free, olive, rights

    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
    F
    0.52
    Player
    0.49
    s
    0.48
    match
    0.47
    后续
    0.46
    -:
    0.46
     Enroll
    0.46
    Legends
    0.45
    life
    0.45
    point
    0.45
    POSITIVE LOGITS
    ále
    0.56
     générateur
    0.52
     recipro
    0.48
    ozione
    0.48
    ó
    0.48
     commemorating
    0.48
    していた
    0.47
     aiguë
    0.47
    蜱
    0.47
    ü
    0.46
    Activations Density 0.000%

    No Known Activations