© 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. 63032
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     utilisation
    -0.90
    tactez
    -0.86
     fiscales
    -0.86
     Hoteles
    -0.84
    lates
    -0.84
    ndry
    -0.83
     señales
    -0.81
    极了
    -0.81
    ógicos
    -0.81
     carretera
    -0.81
    POSITIVE LOGITS
    con
    0.89
    vv
    0.88
    ду
    0.85
    aba
    0.85
    tic
    0.83
    qu
    0.81
    aw
    0.80
    ing
    0.78
    lied
    0.78
    alg
    0.77
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.