© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 35789
    Prev
    Next
    INDEX
    Explanations

    numerical strings and identifiers

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

    The neuron strongly activates on numeric tokens, i.e. sequences of digits.

    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
     móg
    -1.24
    jeka
    -1.20
    terus
    -1.16
     forro
    -1.11
     jestem
    -1.09
     in
    -1.08
     Zusammenfassung
    -1.08
     who
    -1.07
     営業
    -1.06
     at
    -1.05
    POSITIVE LOGITS
    1
    1.18
    2
    1.17
     trover
    1.15
    كيفية
    1.13
    Especially
    1.08
     peuvent
    1.07
     requiere
    1.06
    7
    1.06
    0
    1.06
    منبع
    1.05
    Activations Density 0.012%

    No Known Activations