© 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. 57898
    Prev
    Next
    INDEX
    Explanations

    hardware, versions, and specific names

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

    The neuron primarily activates on numeric tokens or numeric sequences (e.g., version numbers, literal numbers, and digit strings).

    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
     ۱۴۰۰
    -0.88
    androidx
    -0.82
    琀
    -0.79
     TikTok
    -0.78
    scryfall
    -0.75
     ۱۳
    -0.72
    localctx
    -0.72
     Columb
    -0.71
     polymerization
    -0.71
     uninten
    -0.70
    POSITIVE LOGITS
    rifft
    0.92
    随意
    0.88
     Рим
    0.84
     Mocha
    0.82
     xrange
    0.81
    isent
    0.80
    édition
    0.80
     spost
    0.79
     FANDOM
    0.79
    turma
    0.79
    Activations Density 0.006%

    No Known Activations