© 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. 102852
    Prev
    Next
    INDEX
    Explanations

    encoded data or strings

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

    the word "encoded" in technical or programming contexts.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    This neuron activates on occurrences of the word “encoded.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    ’
    -3.34
    a
    -3.05
    埽
    -2.88
    ?”
    -2.86
    i
    -2.84
    C
    -2.77
    ᠂
    -2.72
    ,”
    -2.53
    ￬
    -2.50
    and
    -2.48
    POSITIVE LOGITS
    灕
    2.83
    焄
    2.73
    逯
    2.55
    訛
    2.53
    昝
    2.52
    鳝
    2.50
    ܜ
    2.50
    欵
    2.48
    zelfde
    2.48
     शुर
    2.47
    Activations Density 0.012%

    No Known Activations