© 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. 236671
    Prev
    Next
    INDEX
    Explanations

    used, with, or by

    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
     Lords
    0.48
     promover
    0.47
     عر
    0.47
    鵑
    0.46
     Sanitation
    0.46
     lords
    0.46
     Elf
    0.46
     los
    0.46
    cribing
    0.45
     الملك
    0.45
    POSITIVE LOGITS
    effect
    0.48
    кара
    0.48
    Gesture
    0.48
    corporate
    0.44
    "></
    0.44
    技能
    0.43
    experimental
    0.43
    技巧
    0.42
    electrical
    0.42
    explorer
    0.41
    Activations Density 0.001%

    No Known Activations