© 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. 196078
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation

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

    beyond these, cause skin, FDACS permit, Amount B

    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
    }
    0.45
     nhất
    0.43
     Istituto
    0.42
     quarterly
    0.41
    }\
    0.40
     maintaining
    0.40
    绛
    0.40
     mq
    0.39
     transcript
    0.39
     Justiça
    0.39
    POSITIVE LOGITS
     ステン
    0.55
     हैन
    0.54
     సై
    0.50
    🇴
    0.50
    тено
    0.49
    farbe
    0.48
    appui
    0.48
    ifilm
    0.48
     अंध
    0.47
     從
    0.46
    Activations Density 0.000%

    No Known Activations