© 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. 92841
    Prev
    Next
    INDEX
    Explanations

    James Davison

    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
    AAT
    -0.82
    autant
    -0.82
    Slee
    -0.77
    桅
    -0.76
    Panamoan
    -0.73
    ﻹ
    -0.73
    咔
    -0.73
    ᛅ
    -0.73
     considér
    -0.72
    chevrolet
    -0.72
    POSITIVE LOGITS
     Ca
    0.83
     blobs
    0.82
     aliases
    0.79
    net
    0.76
    Cu
    0.76
     Blob
    0.75
     wyposaż
    0.75
    Santa
    0.75
     Cuff
    0.73
    Ca
    0.72
    Activations Density 0.020%

    No Known Activations