© 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. 79358
    Prev
    Next
    INDEX
    Explanations

    additional legal or interpretative text

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

    away from, where, pragmatism

    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
     单
    0.48
     olmadığı
    0.47
     باقي
    0.46
     únicamente
    0.46
    ließlich
    0.44
    BeerItem
    0.43
     Runners
    0.43
    lone
    0.43
     डबल
    0.43
    šć
    0.43
    POSITIVE LOGITS
    ーター
    0.44
    徫
    0.42
     schemas
    0.42
     шумо
    0.42
     version
    0.41
     HAD
    0.40
    тно
    0.40
     planas
    0.40
     preventative
    0.39
    版
    0.39
    Activations Density 0.000%

    No Known Activations