© 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. 194347
    Prev
    Next
    INDEX
    Explanations

    category tags, intelligent gestures

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

    new blocks

    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
    arendra
    0.44
     Hazel
    0.44
     Schedules
    0.43
     Haz
    0.42
     Nutrient
    0.41
     Sunni
    0.41
     Disabilities
    0.41
    _
    0.40
    ద్ధి
    0.39
     International
    0.39
    POSITIVE LOGITS
     automáticamente
    0.49
    зел
    0.49
    :',
    0.48
     ':
    0.48
     muñ
    0.48
     automatiquement
    0.47
    డ్
    0.47
    .",[
    0.46
    ಡ್
    0.46
     temer
    0.45
    Activations Density 0.000%

    No Known Activations