© 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. 162548
    Prev
    Next
    INDEX
    Explanations

    journal citations

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

    obtaining ideas, services, or content

    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
     타
    0.39
     אתה
    0.39
    زار
    0.38
    agn
    0.38
    جه
    0.38
    틸
    0.38
    地
    0.37
    OW
    0.36
     땅
    0.36
     Qualquer
    0.36
    POSITIVE LOGITS
     compras
    0.44
     commenting
    0.42
     Cryptocurrency
    0.42
     çalışmaları
    0.42
    買い
    0.42
     предстоя
    0.42
     mevcut
    0.42
     Expenses
    0.41
     таблицу
    0.41
     yakni
    0.40
    Activations Density 0.001%

    No Known Activations