© 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. 158459
    Prev
    Next
    INDEX
    Explanations

    US,Github, doctrine

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

    knowledge graphs and technical terms

    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
     ovo
    0.46
     Rien
    0.44
     conserva
    0.43
     û
    0.43
     abandonar
    0.42
     resear
    0.42
    ië
    0.42
     procédures
    0.42
    팡
    0.42
     Howe
    0.42
    POSITIVE LOGITS
    Doctrine
    0.47
    辅助
    0.46
    Github
    0.45
    doctrine
    0.44
     đậm
    0.43
    偏
    0.43
     기관
    0.42
    EditDialogOpen
    0.41
     codebase
    0.41
    弊社
    0.41
    Activations Density 0.001%

    No Known Activations