© 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. 22-GEMMASCOPE-RES-131K
    7. 14394
    Prev
    Next
    INDEX
    Explanations

    end/begin delimiters

    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
    鹋
    -1.66
    ції
    -1.56
    ！』
    -1.55
    甞
    -1.46
    ECTOS
    -1.46
     裕
    -1.45
    漪
    -1.41
     ANCHE
    -1.40
    HYDR
    -1.40
    Ꮅ
    -1.39
    POSITIVE LOGITS
    T
    1.83
    ↵↵
    1.82
    這些
    1.74
    }$.
    1.68
    S
    1.66
    K
    1.55
     and
    1.53
     мы
    1.52
     \
    1.50
     nossa
    1.50
    Activations Density 0.001%

    No Known Activations