© 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. 148379
    Prev
    Next
    INDEX
    Explanations

    permissions and lawsuits

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

    muscle relaxation

    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
    সার
    0.46
    获奖
    0.46
    од
    0.45
    Football
    0.44
    悛
    0.44
    鐟
    0.44
    དང་
    0.43
    嗉
    0.43
     Mortgage
    0.43
    Funeral
    0.42
    POSITIVE LOGITS
     spasms
    0.55
     fluids
    0.52
     effluents
    0.52
     seizures
    0.51
     headwinds
    0.50
     lawsuits
    0.49
     vesicles
    0.49
    いる
    0.49
     permisos
    0.47
     hectares
    0.47
    Activations Density 0.001%

    No Known Activations