© 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. 174937
    Prev
    Next
    INDEX
    Explanations

    specific adjective-noun pairings

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

    local deployment or implementation

    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
    E
    0.57
    ه
    0.57
    WAY
    0.50
     journalist
    0.49
     rector
    0.49
    Workbench
    0.48
    ES
    0.48
    Le
    0.47
     gobernador
    0.46
    Ủ
    0.46
    POSITIVE LOGITS
    ၇
    0.52
    ippi
    0.48
    ≐
    0.46
    ↓↓
    0.44
    τρι
    0.44
    ∧
    0.44
    🈺
    0.44
    🈂
    0.44
     Consistent
    0.44
    প্রবাসী
    0.44
    Activations Density 0.000%

    No Known Activations