© 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. 190622
    Prev
    Next
    INDEX
    Explanations

    gallery here

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

    perfect corrections, stays pristine

    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
     колеба
    0.53
     macer
    0.50
    
    0.50
     ትንሽ
    0.48
     少し
    0.48
     crebre
    0.47
     немно
    0.47
     мед
    0.47
     yarı
    0.47
    🥶
    0.46
    POSITIVE LOGITS
     Randy
    0.53
    錄
    0.50
     og
    0.47
     eksempel
    0.46
    Randy
    0.46
     Reese
    0.45
    maintained
    0.45
    ൦
    0.44
     Danielle
    0.44
    獎
    0.43
    Activations Density 0.000%

    No Known Activations