© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 86991
    Prev
    Next
    INDEX
    Explanations

    alabama

    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
     Now
    -2.53
     is
    -2.45
     peculiar
    -2.44
     "
    -2.42
     raving
    -2.41
     These
    -2.38
     Of
    -2.30
    -2.28
     pueda
    -2.28
     easing
    -2.20
    POSITIVE LOGITS
    圌
    3.25
    鮃
    2.84
    Ꮂ
    2.70
    馘
    2.67
    ༑
    2.61
    𓋼
    2.52
    ቾ
    2.50
     букет
    2.47
     邸
    2.39
     Gleaner
    2.39
    Activations Density 0.005%

    No Known Activations