© 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. 70231
    Prev
    Next
    INDEX
    Explanations

    action followed by descriptor or date

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

    action, python, and items

    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
     }^{
    0.59
     avion
    0.56
    THz
    0.55
    ◇
    0.54
     obce
    0.54
    {
    0.52
     याचे
    0.52
    ᠯ
    0.50
    ۵
    0.49
    TR
    0.49
    POSITIVE LOGITS
     action
    1.22
     Action
    1.16
    Action
    1.10
    action
    1.07
     ACTION
    1.05
     acción
    1.00
    アクション
    0.98
    getAction
    0.95
    ACTION
    0.95
    动作
    0.95
    Activations Density 0.032%

    No Known Activations