© 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. 34-GEMMASCOPE-RES-131K
    7. 31979
    Prev
    Next
    INDEX
    Explanations

    IP camera

    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_34/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
    ateľ
    -0.69
     nadzie
    -0.68
     weird
    -0.64
     Eight
    -0.63
     strives
    -0.63
     excel
    -0.62
     these
    -0.62
     Four
    -0.62
     headquarters
    -0.61
    reven
    -0.61
    POSITIVE LOGITS
     ?
    0.88
    änä
    0.83
     Whelan
    0.80
    Utc
    0.79
    CUL
    0.79
    azgo
    0.78
    τευ
    0.78
     precondition
    0.77
    ParseTree
    0.76
     Bonjour
    0.75
    Activations Density 0.004%

    No Known Activations