© 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. 10-GEMMASCOPE-RES-131K
    7. 58797
    Prev
    Next
    INDEX
    Explanations

    listing items

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

    The neuron is primarily detecting numeric tokens (e.g. integers, decimals, percentages) 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_10/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
     also
    -1.42
    ra
    -1.30
     then
    -1.15
    AtIndexPath
    -1.12
    比较好
    -1.11
     
    -1.11
    ap
    -1.09
    ke
    -1.07
    </b>
    -1.07
    lighted
    -1.05
    POSITIVE LOGITS
     our
    1.87
     Перейти
    1.30
     Welche
    1.30
    consola
    1.29
    erti
    1.29
    壠
    1.27
     Siehe
    1.27
     Entdecke
    1.27
     vesel
    1.25
    ::$_
    1.24
    Activations Density 0.246%

    No Known Activations