© 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. 241158
    Prev
    Next
    INDEX
    Explanations

    programmes

    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
    á
    0.57
    ORO
    0.49
    ES
    0.49
     überprü
    0.49
     لأن
    0.49
    ORT
    0.48
     impon
    0.48
     exercício
    0.48
    出于
    0.48
    تبط
    0.48
    POSITIVE LOGITS
    इंडियन
    0.49
    )،
    0.44
     regenerating
    0.44
    །
    0.43
    レンジ
    0.42
     پروگرام
    0.42
     kingdom
    0.41
    )।
    0.41
     डाय
    0.41
    ).)
    0.41
    Activations Density 0.000%

    No Known Activations