© 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. 31560
    Prev
    Next
    INDEX
    Explanations

    code comment markers

    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
     dobr
    -0.96
     navideños
    -0.96
     reorganization
    -0.96
     doulou
    -0.95
     kesi
    -0.93
     météo
    -0.93
     vás
    -0.93
    niei
    -0.91
     colgantes
    -0.90
    -0.90
    POSITIVE LOGITS
     Un
    0.89
     to
    0.88
    zbęd
    0.86
    jo
    0.84
    監
    0.84
    zawa
    0.82
    ha
    0.82
    To
    0.82
    These
    0.81
    ru
    0.81
    Activations Density 0.008%

    No Known Activations