© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 84131
    Prev
    Next
    INDEX
    Explanations

    citations and abbreviations

    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
    هو
    -0.92
     cốc
    -0.90
    Fotografía
    -0.84
     nouveautés
    -0.83
    gsmål
    -0.79
     '';
    -0.78
    }$,
    -0.78
     Portail
    -0.77
    jących
    -0.77
    }$.
    -0.77
    POSITIVE LOGITS
    яг
    0.93
     myriad
    0.90
    same
    0.83
    óż
    0.81
    InputElement
    0.81
    随后
    0.80
    細い
    0.80
    TypeList
    0.80
    uin
    0.79
    during
    0.78
    Activations Density 0.134%

    No Known Activations