© 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. 34-GEMMASCOPE-RES-131K
    7. 90912
    Prev
    Next
    INDEX
    Explanations

    angular component files

    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
    hdys
    -0.76
    рите
    -0.75
    Hib
    -0.73
    ซี
    -0.72
     complicated
    -0.71
    minen
    -0.71
    HttpEntity
    -0.68
    usuario
    -0.67
    كم
    -0.67
    bParam
    -0.66
    POSITIVE LOGITS
     module
    0.99
     tjen
    0.98
     Pipe
    0.85
     providers
    0.83
     LIK
    0.80
     Garda
    0.80
     prevenir
    0.79
    module
    0.79
     WOULD
    0.79
    Pipes
    0.78
    Activations Density 0.026%

    No Known Activations