© 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. 10-GEMMASCOPE-RES-131K
    7. 113177
    Prev
    Next
    INDEX
    Explanations

    summary followed by descriptions

    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_10/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
     The
    -4.06
     --
    -2.88
     are
    -2.77
     podem
    -2.67
     crucial
    -2.67
     Is
    -2.66
     '
    -2.64
     !!!!
    -2.64
     VERY
    -2.64
    },
    -2.63
    POSITIVE LOGITS
    鋮
    3.33
    韪
    3.02
    呖
    2.94
    题材
    2.92
    最后由
    2.89
     शुर
    2.84
    古风
    2.80
    ेमाल
    2.72
    誊
    2.72
    縯
    2.70
    Activations Density 0.012%

    No Known Activations