© 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. 52423
    Prev
    Next
    INDEX
    Explanations

    information processing consequence

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

    model on

    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
     तथ्य
    0.43
     Stores
    0.42
     Elderly
    0.41
    !==
    0.40
     Streets
    0.40
    പം
    0.40
     Fleet
    0.39
     whichever
    0.39
     đựng
    0.39
    么
    0.39
    POSITIVE LOGITS
    agir
    0.45
     туда
    0.45
    qualität
    0.43
     krypt
    0.43
     VIH
    0.43
     Фу
    0.43
     Variablen
    0.43
     corrupción
    0.42
     laboris
    0.42
    カット
    0.42
    Activations Density 0.000%

    No Known Activations