© 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. 121413
    Prev
    Next
    INDEX
    Explanations

    legal citations

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

    legal citations

    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
     கிரே
    0.48
    学员
    0.42
     போட்டி
    0.42
    ஷ
    0.41
    
    0.41
    耳机
    0.40
    俩
    0.40
    szer
    0.39
     पवन
    0.39
    oticons
    0.39
    POSITIVE LOGITS
    getMinimum
    0.39
     appears
    0.38
    бити
    0.38
     believe
    0.38
    虏
    0.38
    ifiable
    0.38
     usable
    0.37
    вши
    0.37
     spent
    0.37
     negotiation
    0.37
    Activations Density 0.003%

    No Known Activations