© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 95708
    Prev
    Next
    INDEX
    Explanations

    numbers followed by punctuation

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

    This neuron selectively activates on numeric tokens (digits and multi‐digit numbers), i.e. it detects numbers 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
    İM
    -1.07
     DEVICES
    -1.05
    はその
    -1.04
    
    -1.04
     Să
    -1.04
    kkelen
    -1.03
    tidase
    -1.03
    LEBR
    -1.03
     of
    -1.02
     Aeropuerto
    -1.00
    POSITIVE LOGITS
     and
    1.24
    seguida
    1.20
    了两
    1.08
    rsquo
    1.04
    rightarrow
    0.99
    –
    0.98
    了她
    0.94
    了下去
    0.93
    了下
    0.93
    -
    0.93
    Activations Density 0.001%

    No Known Activations