© 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. 148467
    Prev
    Next
    INDEX
    Explanations

    winners, schools, Southern

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

    Uncertainty Principle, neighboring voxels

    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
    продук
    0.47
    管控
    0.45
    숑
    0.45
    흄
    0.45
     Geschäftsführer
    0.44
     FINANCE
    0.44
    汪
    0.44
    삵
    0.44
     방문
    0.44
     акций
    0.43
    POSITIVE LOGITS
    ing
    0.57
     amazingly
    0.53
     Satellite
    0.50
     caiu
    0.49
     farthest
    0.48
     instantaneous
    0.48
     Trib
    0.46
     instantaneously
    0.46
     attracting
    0.45
     literally
    0.45
    Activations Density 0.001%

    No Known Activations