© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 71312
    Prev
    Next
    INDEX
    Explanations

    code, questions or descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     that
    -1.18
    któ
    -1.03
    змом
    -0.96
     esigen
    -0.93
    verez
    -0.93
     within
    -0.92
     though
    -0.91
     rằng
    -0.91
    orex
    -0.91
     možné
    -0.90
    POSITIVE LOGITS
    复杂的
    1.00
    *}$
    0.98
    ɟ
    0.94
    联网
    0.93
    Naturally
    0.92
     wist
    0.91
    
    0.90
    NUMX
    0.89
     Cedex
    0.89
     испы
    0.88
    Activations Density 0.001%

    No Known Activations