© 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. 1352
    Prev
    Next
    INDEX
    Explanations

    proper nouns and code identifiers

    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
    埝
    -2.61
    沨
    -2.59
    pecabe
    -2.41
    تیجه
    -2.41
    磲
    -2.33
    ꪔ
    -2.30
    眥
    -2.25
    ጧ
    -2.23
    偌
    -2.23
     jaké
    -2.23
    POSITIVE LOGITS
    r
    2.67
    。
    2.67
    or
    2.63
    這個
    2.63
    The
    2.44
    s
    2.44
    This
    2.36
    ments
    2.31
    这个
    2.28
    you
    2.23
    Activations Density 0.019%

    No Known Activations