© 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. 10-GEMMASCOPE-RES-131K
    7. 68814
    Prev
    Next
    INDEX
    Explanations

    telephone numbers, extensions, or codes

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

    The neuron specifically detects numeric tokens—especially multi-digit codes and phone extension 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_10/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
    袛
    -1.61
     CheckBox
    -1.48
     miſ
    -1.47
     issus
    -1.46
     certains
    -1.44
    quickly
    -1.44
    薆
    -1.43
     wirk
    -1.41
     BOOK
    -1.41
     that
    -1.39
    POSITIVE LOGITS
     or
    2.25
     at
    2.19
    5
    1.59
     There
    1.49
     for
    1.48
    7
    1.48
     These
    1.45
    9
    1.43
    after
    1.40
     from
    1.39
    Activations Density 0.002%

    No Known Activations