© 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. 55245
    Prev
    Next
    INDEX
    Explanations

    points, ranks, or quantities

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

    city and cyberpunk settings

    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
     Examples
    0.50
     Essays
    0.49
     Kit
    0.45
     लिहाज
    0.45
     ت
    0.44
     examples
    0.44
    ↵
    0.43
     Example
    0.43
     Question
    0.43
     Theory
    0.43
    POSITIVE LOGITS
    淳
    0.48
    ခံ
    0.47
    ಿಸಲಾಗಿದೆ
    0.46
    队友
    0.46
    inação
    0.46
    ométrique
    0.46
    怿
    0.45
    लाईन
    0.45
    ដំណ
    0.44
    オブ
    0.44
    Activations Density 0.000%

    No Known Activations