© 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. 34623
    Prev
    Next
    INDEX
    Explanations

    animal hospital

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

    safety concerns and services

    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
     warl
    0.47
    ⚔
    0.46
    uits
    0.45
    armed
    0.44
    uze
    0.44
     Glückwunsch
    0.43
     Архі
    0.43
    毁灭
    0.42
    ectonic
    0.41
    req
    0.41
    POSITIVE LOGITS
     trasera
    0.41
    服務
    0.41
     servicios
    0.41
     entren
    0.41
    써
    0.40
     ahorro
    0.40
    蘿
    0.39
    서비스
    0.39
    뺀
    0.39
     servicio
    0.38
    Activations Density 0.000%

    No Known Activations