© 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. 254097
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     شرطونه
    0.54
    urlString
    0.52
     дать
    0.50
    蜷
    0.49
     眼
    0.49
     упраж
    0.48
    ó
    0.48
     ドラ
    0.47
    ט
    0.47
     изда
    0.47
    POSITIVE LOGITS
     synergistic
    0.48
     genders
    0.44
     migration
    0.44
     dependence
    0.44
     communities
    0.43
     suburbs
    0.43
     liquidity
    0.42
     nervous
    0.42
     hospitality
    0.42
     dependency
    0.42
    Activations Density 0.000%

    No Known Activations