© 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. 151310
    Prev
    Next
    INDEX
    Explanations

    official London

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

    beyond basic concepts

    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
     बाउ
    0.44
    ग
    0.44
    斑
    0.44
    opl
    0.42
     upkeep
    0.42
     पीढ़ी
    0.42
    慌
    0.41
     মাথা
    0.41
    ﮔ
    0.41
     Instruction
    0.40
    POSITIVE LOGITS
    Siehe
    0.54
    定める
    0.52
     היה
    0.49
     πρω
    0.48
     doce
    0.47
     meninos
    0.47
    ালোচনা
    0.46
    Denne
    0.46
     Rajiv
    0.46
     jornadas
    0.46
    Activations Density 0.000%

    No Known Activations