© 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. 132030
    Prev
    Next
    INDEX
    Explanations

    without departing

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

    the differences between X and Y

    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
     九
    0.56
    旋
    0.52
    九
    0.51
    REGION
    0.50
     Ninth
    0.47
    块
    0.47
    区域
    0.46
    SECOND
    0.46
    旋转
    0.46
    DIVISION
    0.46
    POSITIVE LOGITS
     modifiers
    0.64
     extremities
    0.50
     extractor
    0.50
     expedited
    0.50
     combust
    0.49
     standardized
    0.48
    髡
    0.48
     Eval
    0.47
     alcohols
    0.47
     standardised
    0.46
    Activations Density 0.000%

    No Known Activations