© 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. 109477
    Prev
    Next
    INDEX
    Explanations

    year old, reduce consumption

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

    old, garage, control, couch, figure, simply

    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
    ↵↵
    0.48
    ı
    0.46
     n
    0.45
    -
    0.45
     <
    0.45
    fixes
    0.44
     spaw
    0.44
     *
    0.44
    elli
    0.43
    ן
    0.43
    POSITIVE LOGITS
    ாகு
    0.52
    ರುಗ
    0.50
    իր
    0.47
     ascertaining
    0.46
    USER
    0.46
    인이
    0.46
    και
    0.46
    告
    0.46
    ἀ
    0.46
     condensing
    0.45
    Activations Density 0.000%

    No Known Activations