© 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. 33884
    Prev
    Next
    INDEX
    Explanations

    options or keywords

    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
     Équipe
    -0.94
     potere
    -0.91
    ֵּ
    -0.90
     Sécurité
    -0.90
     proceed
    -0.90
     edifici
    -0.88
    thode
    -0.87
    ִּ
    -0.86
    thodes
    -0.84
     Présentation
    -0.84
    POSITIVE LOGITS
    ⸝
    0.93
     sentimental
    0.83
     объя
    0.83
    大多数
    0.82
     tornado
    0.79
     plupart
    0.79
    ʡ
    0.78
     далеко
    0.77
    見えます
    0.77
    掉了
    0.75
    Activations Density 0.006%

    No Known Activations