© 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. 71422
    Prev
    Next
    INDEX
    Explanations

    reflective context

    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
    ar
    -2.78
    ing
    -2.73
    s
    -2.67
     proverbial
    -2.66
    ↵↵
    -2.53
     ”
    -2.52
    }
    -2.50
    a
    -2.48
    ?
    -2.39
    =
    -2.36
    POSITIVE LOGITS
    趼
    3.05
    骓
    2.97
    ization
    2.83
    －－－－
    2.73
    ｛
    2.73
    ции
    2.70
    婓
    2.66
    ！"
    2.64
    ："
    2.63
    各自
    2.59
    Activations Density 0.001%

    No Known Activations