© 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. 55563
    Prev
    Next
    INDEX
    Explanations

    save, sisters, surface, sales, q

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

    lists, pointers, and indicators

    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
     подо
    0.49
     πολύ
    0.48
     Liye
    0.45
    legt
    0.45
     될
    0.45
    olot
    0.45
    ledge
    0.43
     관련된
    0.43
    tol
    0.43
     カード
    0.42
    POSITIVE LOGITS
    店家
    0.49
     fosse
    0.48
     projet
    0.48
     entrev
    0.48
     SALES
    0.47
     governador
    0.47
    嗱
    0.47
     ถ
    0.46
    ْع
    0.46
     mesta
    0.46
    Activations Density 0.000%

    No Known Activations