© 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. 182894
    Prev
    Next
    INDEX
    Explanations

    ALARP requirement

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

    ** explains drying time

    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
    It
    0.47
     capitalists
    0.46
     느낌
    0.43
     bothers
    0.43
    ὤ
    0.42
    amboat
    0.41
    ţii
    0.41
    Bills
    0.41
    ç
    0.41
    foregroundColor
    0.40
    POSITIVE LOGITS
     pierwsze
    0.48
     обслу
    0.47
     பெரும்பாலான
    0.47
     पढ़ाया
    0.46
    culpa
    0.45
     பெரும்ப
    0.44
    เชื้อ
    0.43
     vždy
    0.43
    ODBA
    0.43
     jind
    0.42
    Activations Density 0.000%

    No Known Activations