© 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. 72245
    Prev
    Next
    INDEX
    Explanations

    URLs and code snippets

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

    This neuron detects numeric tokens or numeric sequences (digits, numbers, or numbers with punctuation) 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
     jiné
    -1.13
     sprend
    -1.08
     kurios
    -1.06
    ότη
    -1.05
     kuris
    -1.02
     uovo
    -1.02
    эффици
    -1.02
    本日は
    -1.01
    我が家の
    -1.00
    ZIONE
    -0.99
    POSITIVE LOGITS
    de
    1.07
    朱印
    1.00
    付ける
    1.00
     Résultat
    0.93
     régime
    0.92
     MÁ
    0.92
     ign
    0.91
    龶
    0.91
     карту
    0.91
    TING
    0.90
    Activations Density 0.011%

    No Known Activations