© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 27512
    Prev
    Next
    INDEX
    Explanations

    numbers preceding digits

    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
     it
    -2.23
    ๒
    -2.14
     Popis
    -2.13
    lgari
    -2.06
    
    -2.05
    知道
    -2.00
     that
    -2.00
     Você
    -1.93
    حض
    -1.91
    先は
    -1.83
    POSITIVE LOGITS
    2
    4.38
    5
    3.31
    3
    3.22
    nd
    3.00
    7
    2.98
    4
    2.92
    6
    2.88
    9
    2.81
    0
    2.77
    8
    2.63
    Activations Density 0.752%

    No Known Activations