© 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. 39776
    Prev
    Next
    INDEX
    Explanations

    deep sofa

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

    training sections

    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
    ath
    0.49
    퀘
    0.49
    constitutional
    0.48
    regulation
    0.48
    ċ
    0.48
    disk
    0.46
    authorization
    0.45
    yleg
    0.45
    antenna
    0.45
    5
    0.44
    POSITIVE LOGITS
     puntual
    0.54
     procedente
    0.54
     eum
    0.52
     önemlidir
    0.51
     intensify
    0.51
     Veränder
    0.50
     Veränderungen
    0.50
     ей
    0.49
     toma
    0.49
     pedestal
    0.49
    Activations Density 0.000%

    No Known Activations