© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 22550
    Prev
    Next
    INDEX
    Explanations

    hexadecimal identifiers

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

    The neuron fires strongly on long hexadecimal identifier strings (e.g. git commit hashes or similar long hex sequences).

    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
     and
    -3.08
     in
    -2.44
     to
    -2.02
     he
    -1.97
     under
    -1.88
     or
    -1.66
     в
    -1.64
     společnost
    -1.62
     by
    -1.60
     \
    -1.59
    POSITIVE LOGITS
     peluche
    2.44
    这些
    2.33
     caricatura
    2.25
     pantalon
    2.25
     diki
    2.14
    鯓
    2.11
     mété
    2.06
     polaire
    2.05
     möjlighet
    2.05
    They
    1.98
    Activations Density 0.017%

    No Known Activations