© 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. 10-GEMMASCOPE-RES-131K
    7. 101221
    Prev
    Next
    INDEX
    Explanations

    fall and subsequent state

    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
    倂
    -2.17
    あるので
    -1.94
    สำหรับ
    -1.89
    鐽
    -1.84
    ズニー
    -1.83
    6
    -1.80
    琿
    -1.79
    峮
    -1.77
    汩
    -1.73
    udades
    -1.71
    POSITIVE LOGITS
     into
    2.48
    </h2>
    1.98
    ;
    1.79
     from
    1.75
     Zustand
    1.74
    〝
    1.73
     out
    1.70
     アンド
    1.66
    please
    1.66
    他还
    1.66
    Activations Density 0.010%

    No Known Activations