© 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. 96374
    Prev
    Next
    INDEX
    Explanations

    Official rules, HIGH activity, Korean delegation

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

    speculation and reasoning

    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
    ૄ
    0.61
    léans
    0.54
    англ
    0.51
    LLY
    0.50
    '),
    0.50
    те
    0.49
    ле
    0.48
    䄸
    0.48
     ана
    0.47
    FFFF
    0.47
    POSITIVE LOGITS
     explicación
    0.46
     Descriptive
    0.45
     hyaluronic
    0.45
     diberikan
    0.45
    给定
    0.44
     Description
    0.44
     Argument
    0.44
     Period
    0.43
     Peptide
    0.43
     Descriptions
    0.41
    Activations Density 0.000%

    No Known Activations