© 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. 16255
    Prev
    Next
    INDEX
    Explanations

    mathematical or code structures

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

    This neuron activates on parts of numeric expressions (digits, decimal points, minus signs, slashes) and thus detects number tokens.

    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
    z
    -1.16
    v
    -0.98
     of
    -0.92
     Resolución
    -0.90
     pestil
    -0.88
    tazione
    -0.82
     volverá
    -0.81
    lij
    -0.81
     ресторан
    -0.81
     więks
    -0.80
    POSITIVE LOGITS
     resina
    1.13
     barata
    1.12
    CLUDING
    1.10
    ٣
    1.05
     caros
    1.04
     ingrediente
    1.04
     hierbas
    1.02
     capot
    1.02
     bertambah
    1.02
     vannak
    1.02
    Activations Density 0.066%

    No Known Activations