© 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. 147926
    Prev
    Next
    INDEX
    Explanations

    raised him

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

    AI, tech, hosting, code, solutions, tools

    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
     MAINTENANCE
    0.49
    कत
    0.48
    защи
    0.46
    銷
    0.46
    я
    0.45
     güneş
    0.45
     обновления
    0.45
     Alaska
    0.44
     chưa
    0.44
     actualización
    0.44
    POSITIVE LOGITS
    Neben
    0.48
    Aub
    0.48
     তারপরে
    0.46
    Liam
    0.46
    郯
    0.46
    Act
    0.46
    Col
    0.46
    Due
    0.45
    Chel
    0.44
    Ň
    0.44
    Activations Density 0.001%

    No Known Activations