© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 86260
    Prev
    Next
    INDEX
    Explanations

    All Star

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

    This neuron is specialized for detecting long hexadecimal identifiers (e.g., commit/file hashes or other hex‐encoded IDs) in code and data.

    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
     juſ
    -1.83
     electricidad
    -1.63
    ##
    -1.60
     ſtand
    -1.55
    卽
    -1.52
     drenaje
    -1.51
     dinosaurios
    -1.51
    殒
    -1.50
     impresionantes
    -1.50
     officio
    -1.48
    POSITIVE LOGITS
    But
    1.80
     with
    1.73
     another
    1.63
     any
    1.55
     able
    1.53
     sebenar
    1.49
     may
    1.48
     an
    1.48
     aspects
    1.48
     the
    1.45
    Activations Density 0.006%

    No Known Activations