© 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. 67821
    Prev
    Next
    INDEX
    Explanations

    code structure and data definition

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

    The neuron activates on numeric tokens (digits and number literals) 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
    cheque
    -1.24
     bahagia
    -1.22
    geladen
    -1.21
    лее
    -1.20
    pence
    -1.17
    beit
    -1.15
     vokal
    -1.15
    speaking
    -1.13
    био
    -1.13
    wendige
    -1.13
    POSITIVE LOGITS
     was
    1.51
     no
    1.27
     used
    1.21
     time
    1.16
     use
    1.13
    ></
    1.08
    往前
    1.07
     did
    1.05
     done
    1.01
     reason
    1.00
    Activations Density 0.014%

    No Known Activations