© 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. 234823
    Prev
    Next
    INDEX
    Explanations

    technical or specific names

    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
     सप्टेंबर
    0.50
    tourism
    0.49
    <unused54>
    0.47
    component
    0.46
    তুম
    0.46
    dollars
    0.46
    <unused65>
    0.44
    זי
    0.44
    除く
    0.43
    舊
    0.43
    POSITIVE LOGITS
     достига
    0.45
     ponytail
    0.44
     godly
    0.44
     Takashi
    0.44
     Unicode
    0.44
    odore
    0.44
     Miy
    0.44
     Tach
    0.43
     cuerda
    0.43
     zah
    0.43
    Activations Density 0.001%

    No Known Activations