© 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. 36440
    Prev
    Next
    INDEX
    Explanations

    code and structured data

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

    This neuron activates on numeric tokens (any sequence of digits), i.e. it detects numbers.

    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
     These
    -1.56
     or
    -1.32
     It
    -1.26
     This
    -1.24
     Some
    -1.21
    These
    -1.17
     There
    -1.11
    ₱
    -1.04
     While
    -1.03
    Chloro
    -1.03
    POSITIVE LOGITS
     poliuret
    1.22
    
    1.17
    歘
    1.17
     tinte
    1.16
     prohi
    1.16
     raio
    1.14
     navide
    1.13
     musst
    1.11
     nuest
    1.11
     munc
    1.09
    Activations Density 0.004%

    No Known Activations