© 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. 67038
    Prev
    Next
    INDEX
    Explanations

    horror genre

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

    gas and battery usage

    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
    Remember
    0.49
    ництва
    0.48
    نڈ
    0.46
    People
    0.46
    Ingredient
    0.45
    }-${
    0.45
     وده
    0.45
    氢
    0.45
    ництво
    0.45
    Hydrogen
    0.44
    POSITIVE LOGITS
     Vá
    0.54
     fast
    0.52
    ún
    0.51
     point
    0.51
     Vold
    0.51
     report
    0.50
     показатель
    0.49
    na
    0.49
     bomb
    0.49
    din
    0.49
    Activations Density 0.000%

    No Known Activations