© 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. 202448
    Prev
    Next
    INDEX
    Explanations

    professional services and expertise

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

    stood sentinel

    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
     অনুভব
    0.48
    ROff
    0.47
     童
    0.46
     люб
    0.46
    大幅
    0.46
    សំណ
    0.46
    绚
    0.45
     រ
    0.45
    艷
    0.44
    色彩
    0.43
    POSITIVE LOGITS
     dati
    0.50
    טי
    0.47
     Maarten
    0.44
    наў
    0.44
    concert
    0.43
    Let
    0.43
    tech
    0.43
     Vincent
    0.43
     giv
    0.43
     giusta
    0.43
    Activations Density 0.000%

    No Known Activations