© 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. 70466
    Prev
    Next
    INDEX
    Explanations

    fan reactions

    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
     such
    -2.02
     on
    -1.75
     each
    -1.73
     many
    -1.72
     both
    -1.70
     using
    -1.68
     what
    -1.60
     our
    -1.56
     about
    -1.53
     other
    -1.51
    POSITIVE LOGITS
     terão
    1.47
     poderão
    1.45
     prochains
    1.43
    『
    1.43
    なんか
    1.43
    你们
    1.41
    Οι
    1.40
    няют
    1.39
    ㄷ
    1.38
    Анна
    1.36
    Activations Density 0.025%

    No Known Activations