© 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. 19484
    Prev
    Next
    INDEX
    Explanations

    programming pointers and data binding

    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
    the
    -2.44
    Ꮚ
    -1.96
    厹
    -1.76
    四处
    -1.76
    𐀀
    -1.75
    鲩
    -1.74
    蛱
    -1.71
    ↵↵
    -1.69
    not
    -1.68
     seront
    -1.68
    POSITIVE LOGITS
     provides
    1.90
     These
    1.88
    ၞ
    1.80
     or
    1.70
     and
    1.70
    乃至
    1.67
     as
    1.66
    Эти
    1.66
     on
    1.63
    을
    1.63
    Activations Density 0.001%

    No Known Activations