© 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. 34-GEMMASCOPE-RES-131K
    7. 1915
    Prev
    Next
    INDEX
    Explanations

    URLs and file paths

    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
    niczy
    -0.84
     яйцо
    -0.82
     mitochondrial
    -0.78
     febrero
    -0.78
    เดือน
    -0.76
    煕
    -0.75
     Recreation
    -0.75
    Following
    -0.74
     using
    -0.74
     APPELLANT
    -0.74
    POSITIVE LOGITS
     erhi
    0.94
     sacrifices
    0.89
     occa
    0.86
     outlay
    0.82
    conductivity
    0.81
    かもしれない
    0.81
     INCLUDES
    0.81
    主要是
    0.81
    álu
    0.81
    ReLU
    0.80
    Activations Density 0.001%

    No Known Activations