© 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. 78244
    Prev
    Next
    INDEX
    Explanations

    FAK, Fach, Fagg, Falk

    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
    ónicas
    -0.78
    UIM
    -0.77
     метра
    -0.77
    empuan
    -0.75
    ADI
    -0.75
    vium
    -0.74
    FormControl
    -0.74
     Shimizu
    -0.73
    kách
    -0.73
    shutdown
    -0.72
    POSITIVE LOGITS
     Frag
    0.72
     DATES
    0.70
     Greco
    0.70
    Eksteraj
    0.69
    "%
    0.69
     consiguió
    0.68
    ıc
    0.68
     BENE
    0.67
    vata
    0.67
     Binding
    0.67
    Activations Density 0.024%

    No Known Activations