© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 2941
    Prev
    Next
    INDEX
    Explanations

    conditions are met:

    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
     cachorro
    -1.10
    //////////////
    -1.09
     GUARANTEE
    -1.01
     perché
    -0.98
     immagin
    -0.97
    〛
    -0.95
     encontre
    -0.95
     mükemmel
    -0.93
     transforme
    -0.92
    Wouldn
    -0.92
    POSITIVE LOGITS
    ที่
    1.05
    yAxis
    0.95
    jedi
    0.93
    睥
    0.90
     inert
    0.90
     exile
    0.89
    ptic
    0.89
     tactile
    0.89
     Igbo
    0.88
     sorts
    0.87
    Activations Density 0.033%

    No Known Activations