© 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. 42135
    Prev
    Next
    INDEX
    Explanations

    how costs are built

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

    how free

    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
     vésicules
    0.49
    IZED
    0.46
    LoopBlend
    0.46
    代理
    0.44
     краси
    0.44
     кле
    0.44
     زخ
    0.44
    ู
    0.43
     ску
    0.43
     Бел
    0.42
    POSITIVE LOGITS
    range
    0.46
     nr
    0.45
    place
    0.44
     Carey
    0.43
    🧖
    0.43
     været
    0.43
     ident
    0.43
     Driscoll
    0.42
     Policies
    0.42
     consecutive
    0.42
    Activations Density 0.000%

    No Known Activations