© 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. 113629
    Prev
    Next
    INDEX
    Explanations

    hexadecimal data

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

    hexadecimal digits within technical data formats like code, hashes, cryptographic keys, and memory addresses.

    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
    廰
    -2.09
     the
    -1.95
    苼
    -1.88
    傒
    -1.87
    襌
    -1.77
    轳
    -1.76
    GEBUR
    -1.74
    沵
    -1.73
     écrans
    -1.70
    歟
    -1.70
    POSITIVE LOGITS
     on
    1.80
    </td>
    1.78
     as
    1.70
     without
    1.65
    at
    1.63
     :
    1.59
     by
    1.59
     On
    1.59
     at
    1.57
     with
    1.56
    Activations Density 0.007%

    No Known Activations