© 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. 10-GEMMASCOPE-RES-131K
    7. 65977
    Prev
    Next
    INDEX
    Explanations

    Rome

    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_10/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
    re
    -4.03
    7
    -3.45
    “
    -3.39
    4
    -3.33
    This
    -3.27
    2
    -3.25
    3
    -3.05
    5
    -3.03
    6
    -2.95
    0
    -2.88
    POSITIVE LOGITS
     แต่
    3.02
    狲
    3.00
    鉨
    2.83
    鳙
    2.81
    鲽
    2.72
    ᓕ
    2.63
     programu
    2.61
    
    2.59
    毳
    2.59
     énergie
    2.56
    Activations Density 0.003%

    No Known Activations