© 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. 15740
    Prev
    Next
    INDEX
    Explanations

    track listings

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

    The neuron activates strongly on numeric tokens (sequences of digits or numbers) anywhere in the 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
     like
    -1.20
    ICIENCY
    -1.05
    ७
    -1.04
    UpInside
    -1.03
    ようだ
    -1.02
     plötzlich
    -1.02
     &&
    -1.00
    ३
    -0.99
    ようで
    -0.99
    boBox
    -0.97
    POSITIVE LOGITS
    not
    1.06
     jego
    1.03
    but
    1.02
    が高
    1.02
    lader
    0.98
    すな
    0.97
     حتی
    0.96
     Soldaten
    0.96
    셰
    0.96
    further
    0.96
    Activations Density 0.005%

    No Known Activations