© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 180468
    Prev
    Next
    INDEX
    Explanations

    need for context

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

    park entrance

    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
     tabled
    0.55
     他
    0.52
     ẞ
    0.52
    <unused97>
    0.51
    rparam
    0.50
    
    0.49
     trong
    0.48
     byly
    0.48
     бассей
    0.48
    
    0.48
    POSITIVE LOGITS
    ians
    0.57
    ли
    0.53
    definitions
    0.53
    ט
    0.53
    تي
    0.52
    ت
    0.52
    t
    0.52
    ii
    0.50
    tiles
    0.50
    ado
    0.50
    Activations Density 0.000%

    No Known Activations