© 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. 43219
    Prev
    Next
    INDEX
    Explanations

    technical or specialized terms

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

    nuances and explanations

    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
    าตุ
    0.48
     vâr
    0.45
    โซ
    0.41
     weathering
    0.41
    することで
    0.40
    น
    0.40
    ន
    0.40
     pública
    0.40
     받
    0.39
    ณ
    0.39
    POSITIVE LOGITS
     کي
    0.55
    rischen
    0.49
     nicknamed
    0.48
    详解
    0.48
     دستاویز
    0.48
    ammatory
    0.47
     গুরুতর
    0.47
     விஞ்ஞான
    0.47
     كلمة
    0.46
    pha
    0.46
    Activations Density 0.000%

    No Known Activations