© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 72574
    Prev
    Next
    INDEX
    Explanations

    Java code annotations

    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
    لاه
    -1.16
    lijken
    -1.14
    /<
    -1.14
    tı
    -1.10
     matériel
    -1.08
    
    -1.07
    chaffenheit
    -1.05
     apprend
    -1.04
    ENED
    -1.03
    ividual
    -1.01
    POSITIVE LOGITS
    There
    0.98
     in
    0.94
    舒服
    0.93
     ['./
    0.91
    :
    0.91
    壁纸
    0.90
     klassischen
    0.89
    Because
    0.87
    0.87
    Some
    0.86
    Activations Density 0.001%

    No Known Activations