© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99559
    Prev
    Next
    INDEX
    Explanations

    static print under oath

    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
    tita
    -0.85
     manier
    -0.80
    branche
    -0.77
    isex
    -0.75
     provar
    -0.74
    履き
    -0.73
    ummer
    -0.73
    aui
    -0.73
    uos
    -0.73
     Laat
    -0.72
    POSITIVE LOGITS
     ultra
    0.82
     आहे
    0.75
     widespread
    0.66
     on
    0.65
     zdecydow
    0.65
     very
    0.63
     On
    0.62
     чор
    0.61
     definitely
    0.60
     Neu
    0.60
    Activations Density 0.061%

    No Known Activations