© 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. 34-GEMMASCOPE-RES-131K
    4. 70158
    Prev
    Next
    INDEX
    Explanations

    fax number

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

    The main thing this neuron does is detect numeric tokens (digits and 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_34/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
    chae
    -0.79
    ttps
    -0.75
     checker
    -0.74
     Philharmonic
    -0.73
    wala
    -0.73
    getUid
    -0.73
    iffion
    -0.73
    》
    -0.72
     trachea
    -0.72
     Spotify
    -0.72
    POSITIVE LOGITS
     fax
    5.22
     Fax
    4.34
    Fax
    4.16
    fax
    4.03
    FAX
    3.52
     FAX
    3.48
     fa
    1.88
     facsimile
    1.84
     фак
    1.56
    фак
    1.55
    Activations Density 0.070%

    No Known Activations