© 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. 112933
    Prev
    Next
    INDEX
    Explanations

    standard followed by descriptive noun

    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
    }
    -1.53
     Of
    -1.47
    其中
    -1.44
     áng
    -1.38
     $
    -1.38
     ludicrous
    -1.38
     quí
    -1.37
    もの
    -1.34
     gemessen
    -1.33
    ೣ
    -1.32
    POSITIVE LOGITS
     休閒
    1.88
    »،
    1.76
    ằm
    1.74
    ؛
    1.68
     standard
    1.64
    (´
    1.61
    standard
    1.61
     penilaian
    1.60
     pencarian
    1.59
     cahaya
    1.59
    Activations Density 0.030%

    No Known Activations