© 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. 22-GEMMASCOPE-RES-131K
    7. 65053
    Prev
    Next
    INDEX
    Explanations

    creating new code structures

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

    The neuron detects numeric literals (numbers) in code or text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    部分が
    -0.98
    AppMethodBeat
    -0.96
    祛
    -0.92
    ěř
    -0.91
    ところは
    -0.89
    maybe
    -0.88
    海道
    -0.86
    hemm
    -0.85
     presença
    -0.85
    ῖ
    -0.85
    POSITIVE LOGITS
     with
    1.40
     new
    1.26
     a
    1.24
     an
    1.06
     two
    1.02
    ())){
    0.94
     lepší
    0.93
     moose
    0.92
    dő
    0.90
     rudimentary
    0.90
    Activations Density 0.019%

    No Known Activations