© 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. 30617
    Prev
    Next
    INDEX
    Explanations

    information items

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

    classification and prioritization

    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
     skin
    0.42
     във
    0.41
     muted
    0.40
    DateTime
    0.40
    atura
    0.39
    ↵
    0.38
     sart
    0.38
     skinny
    0.38
    ,
    0.38
    DataSet
    0.37
    POSITIVE LOGITS
     neuest
    0.52
     Änderung
    0.49
     Turnier
    0.46
     ක්‍ර
    0.45
     Schulen
    0.45
     prioridad
    0.45
     divulgação
    0.44
     thefe
    0.43
     tendencias
    0.43
     grandsons
    0.43
    Activations Density 0.000%

    No Known Activations