© 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. 113331
    Prev
    Next
    INDEX
    Explanations

    baseball catcher or baseman

    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
     diki
    -3.11
     kollu
    -2.89
     geldi
    -2.84
    鸶
    -2.83
     kalem
    -2.77
    Hanya
    -2.72
     pauv
    -2.67
     senin
    -2.56
    埸
    -2.55
     bunda
    -2.53
    POSITIVE LOGITS
     
    4.38
    </i>
    3.73
    "
    3.39
    </h3>
    3.13
     “
    2.92
     vollständ
    2.80
    ↵
    2.64
    した
    2.52
     genellikle
    2.52
     sobald
    2.41
    Activations Density 0.008%

    No Known Activations