© 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. 234292
    Prev
    Next
    INDEX
    Explanations

    schedule posts or messages

    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
     комі
    0.49
    ات
    0.49
    怜
    0.49
    ємо
    0.47
     subspaces
    0.47
    єї
    0.46
    їн
    0.45
    蒾
    0.45
    об
    0.44
    єднання
    0.44
    POSITIVE LOGITS
    väl
    0.54
    tr
    0.52
    DATABASE
    0.49
    electronic
    0.48
    ts
    0.48
    DEVICE
    0.47
    raving
    0.46
    গায়
    0.46
    hattam
    0.46
     関
    0.46
    Activations Density 0.001%

    No Known Activations