© 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. 117722
    Prev
    Next
    INDEX
    Explanations

    MIT License

    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
     negras
    -0.89
     vody
    -0.87
     dorada
    -0.85
     dadas
    -0.83
     lobos
    -0.83
     rojas
    -0.82
     directores
    -0.82
    TypedArray
    -0.81
     kapit
    -0.81
     čern
    -0.80
    POSITIVE LOGITS
    apour
    0.85
     없는
    0.80
     obyvateľov
    0.79
    ապ
    0.78
     einger
    0.78
    HALF
    0.77
    Guido
    0.77
    matmul
    0.76
    ITERIA
    0.75
    entieth
    0.75
    Activations Density 0.001%

    No Known Activations