© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 184970
    Prev
    Next
    INDEX
    Explanations

    bonding later, research report

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

    carrion, builder, figure, label, column

    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
     แก้
    0.48
    ándole
    0.47
     ล่ะ
    0.45
    ASH
    0.45
     ລ
    0.43
     spending
    0.43
     시간을
    0.43
     commitment
    0.43
     setInterval
    0.43
     prosecutor
    0.42
    POSITIVE LOGITS
    બાદ
    0.56
    かる
    0.50
    кг
    0.50
    کار
    0.49
    嫵
    0.49
    વાની
    0.49
    tidy
    0.49
    ನಾಡ
    0.49
    詼
    0.48
    है
    0.48
    Activations Density 0.000%

    No Known Activations