© 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. 34113
    Prev
    Next
    INDEX
    Explanations

    all categories

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

    The neuron activates on numerical quantity tokens (numbers and counts) 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
     a
    -1.53
     certain
    -1.21
    aneity
    -1.20
    慙
    -1.16
     whereas
    -1.13
    などの
    -1.13
    男人的
    -1.13
    creens
    -1.12
    ographed
    -1.12
    或者
    -1.11
    POSITIVE LOGITS
     who
    1.61
     age
    1.17
    vět
    1.14
    agisse
    1.12
    jenih
    1.12
     ages
    1.10
     From
    1.09
     来自
    1.08
     from
    1.07
    We
    1.06
    Activations Density 0.028%

    No Known Activations