© 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. 102551
    Prev
    Next
    INDEX
    Explanations

    Class Cast Exception

    np_acts-logits-general · gemini-2.5-flash-lite

    the word "actually" or tokens that are part of proper nouns, technical terms, or specialized vocabulary.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
    灕
    -1.62
    〝
    -1.53
    ższych
    -1.51
     zult
    -1.49
    :
    -1.49
     Following
    -1.48
    ilihan
    -1.48
     únicamente
    -1.45
     still
    -1.43
    </code>
    -1.42
    POSITIVE LOGITS
    鹇
    1.90
    ሖ
    1.86
    眥
    1.82
    犼
    1.75
    l
    1.67
     な
    1.65
    i
    1.64
    an
    1.63
    t
    1.61
    有何
    1.59
    Activations Density 0.000%

    No Known Activations