© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 203520
    Prev
    Next
    INDEX
    Explanations

    city centre, should die, yet to come, fully, thing, leading, downtown

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

    Describe how to do something

    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
     ಸ್ವ
    0.53
    ﻩ
    0.53
    
    0.53
     ಇಲ್ಲಿ
    0.52
     فِي
    0.52
     ⿰
    0.51
     प्रश्नावली
    0.51
    גיע
    0.51
    ','"+
    0.51
     двадцать
    0.50
    POSITIVE LOGITS
     negative
    0.54
    :
    0.53
    v
    0.49
    .
    0.47
     collateral
    0.46
    negative
    0.46
     fiat
    0.44
    Collin
    0.44
     emission
    0.43
     highlight
    0.43
    Activations Density 0.000%

    No Known Activations