© 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. 227700
    Prev
    Next
    INDEX
    Explanations

    permitted to

    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
     ANGELES
    0.55
    ྐ
    0.48
     caminho
    0.47
     ගැනීම
    0.47
    ر
    0.47
    ال
    0.46
     Duque
    0.45
     CHAS
    0.45
     externalities
    0.45
     цикл
    0.45
    POSITIVE LOGITS
    AndWait
    0.45
    }&=
    0.45
     リビング
    0.42
    ’
    0.41
     会
    0.40
    TW
    0.40
     ಏನ
    0.39
    )^
    0.39
     swit
    0.39
    enee
    0.39
    Activations Density 0.000%

    No Known Activations