© 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. 30780
    Prev
    Next
    INDEX
    Explanations

    Dob Wayne Hall

    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
    禾
    -0.75
     ета
    -0.71
     x
    -0.68
     něk
    -0.68
     aquí
    -0.68
     اطراف
    -0.67
     الو
    -0.67
     Wild
    -0.66
     Bob
    -0.66
     subgroup
    -0.66
    POSITIVE LOGITS
     LIMIT
    0.94
    euler
    0.91
    projec
    0.84
     soluzioni
    0.83
     projec
    0.82
    Lattice
    0.80
     stolet
    0.79
    Miejs
    0.79
     wasted
    0.79
     limit
    0.78
    Activations Density 0.057%

    No Known Activations