© 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. 34-GEMMASCOPE-RES-131K
    7. 63828
    Prev
    Next
    INDEX
    Explanations

    Boost C++ library licenses

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

    The neuron strongly activates on isolated numeric tokens (e.g. single digits or version numbers) and code‐style identifiers containing digits or trailing underscores.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    ICA
    -0.75
     hasn
    -0.72
     خارجی
    -0.72
     hadn
    -0.72
    ❘
    -0.71
     professionisti
    -0.70
    áus
    -0.69
    狀態
    -0.68
    刪
    -0.68
     nito
    -0.68
    POSITIVE LOGITS
     Charm
    0.82
    Zd
    0.79
     enorm
    0.78
    RECE
    0.77
    方が
    0.77
     vaste
    0.75
     grossesse
    0.75
    Kaya
    0.73
    вки
    0.73
    gunta
    0.72
    Activations Density 0.003%

    No Known Activations