© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 59856
    Prev
    Next
    INDEX
    Explanations

    programming code and documentation

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

    The neuron strongly activates on tokens containing digits (e.g. version numbers, numeric identifiers, or standalone numbers).

    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
    [@
    -0.75
    Transfer
    -0.71
     ApiException
    -0.69
     Transfer
    -0.69
     перене
    -0.69
    RELEASE
    -0.68
     дума
    -0.66
     unreleased
    -0.66
    ウマ
    -0.66
     Ejecutivo
    -0.65
    POSITIVE LOGITS
    rev
    0.72
    コネ
    0.70
     سن
    0.63
    volt
    0.62
    iveau
    0.60
    が始
    0.60
     Scotch
    0.60
     tờ
    0.59
     Kol
    0.59
    seeker
    0.58
    Activations Density 0.069%

    No Known Activations