© 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. 204963
    Prev
    Next
    INDEX
    Explanations

    describing states or consequences

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

    explaining concepts or documents

    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
     tentar
    0.46
    銨
    0.45
     России
    0.44
     mantenere
    0.44
     rabbits
    0.42
     vecinos
    0.42
    金の
    0.42
     repayment
    0.41
     cột
    0.41
    诿
    0.41
    POSITIVE LOGITS
    MM
    0.50
    ни
    0.47
    sko
    0.47
    INSON
    0.45
    popupIsOpen
    0.45
    vis
    0.45
    osx
    0.45
    никова
    0.44
    腱
    0.44
    ComboBox
    0.43
    Activations Density 0.002%

    No Known Activations