© 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. 22-GEMMASCOPE-RES-131K
    7. 26675
    Prev
    Next
    INDEX
    Explanations

    programming keywords and syntax

    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_22/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
     Zurück
    -0.88
     таких
    -0.82
     самой
    -0.79
     immediate
    -0.78
    Much
    -0.78
     relocated
    -0.77
     perfeito
    -0.77
     लिए
    -0.76
     coraggio
    -0.76
    ailleurs
    -0.74
    POSITIVE LOGITS
    ricanes
    1.05
    RPM
    0.98
    镳
    0.94
    Дереккөздер
    0.94
    ributor
    0.94
    ariate
    0.94
    σσ
    0.93
    fähigkeit
    0.92
    raisal
    0.91
    μμ
    0.91
    Activations Density 0.014%

    No Known Activations