© 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. 102469
    Prev
    Next
    INDEX
    Explanations

    pound

    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
    0
    -3.36
    What
    -2.58
     mientras
    -2.52
    Подготовка
    -2.42
     "
    -2.36
     suele
    -2.34
     suelen
    -2.31
     This
    -2.28
     disfruta
    -2.28
     They
    -2.23
    POSITIVE LOGITS
    ↵↵
    2.67
    女主
    2.52
    礡
    2.45
    踯
    2.41
    氿
    2.39
     NUEVO
    2.34
    涠
    2.34
    礴
    2.31
    ),
    2.28
     VILLAGE
    2.28
    Activations Density 0.007%

    No Known Activations