© 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. 202472
    Prev
    Next
    INDEX
    Explanations

    all tests and routes

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

    code organization and discovery

    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
     Practice
    0.46
     Platform
    0.45
     S
    0.44
     System
    0.44
    microsoft
    0.43
    zh
    0.43
     -*-
    0.43
     Broadcasting
    0.42
     practice
    0.42
    debug
    0.42
    POSITIVE LOGITS
     scan
    0.46
     überall
    0.45
    Scan
    0.42
     вашу
    0.42
     regiões
    0.41
    Joh
    0.41
    Actors
    0.41
    逺
    0.40
     розта
    0.40
     автофо
    0.40
    Activations Density 0.000%

    No Known Activations