© 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. 14220
    Prev
    Next
    INDEX
    Explanations

    recommended citation or options

    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
    }
    -3.20
     当
    -3.16
    ╽
    -2.97
    外的
    -2.95
     When
    -2.88
    小花
    -2.86
     ``
    -2.86
     '
    -2.83
    ꜆
    -2.83
    actéristi
    -2.78
    POSITIVE LOGITS
    鸶
    3.25
    勍
    3.16
    ↵
    3.14
    疍
    3.00
    阇
    2.94
     口コミ
    2.92
    袮
    2.89
    灕
    2.89
     火鍋
    2.81
    Ἦ
    2.81
    Activations Density 0.012%

    No Known Activations