© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 47251
    Prev
    Next
    INDEX
    Explanations

    telephone features

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

    The neuron is a lexical detector for mentions of “telephone” or “phone” (and closely related telephone-device terms).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     komment
    -0.84
    itie
    -0.80
    lassified
    -0.75
     call
    -0.75
    调用
    -0.73
    閡
    -0.72
    👧
    -0.72
    atteindre
    -0.72
     PSYCH
    -0.71
    ক্ষ
    -0.71
    POSITIVE LOGITS
     handset
    0.97
     DSS
    0.82
     SPA
    0.74
     Hand
    0.71
    Voy
    0.69
     retro
    0.69
    unregister
    0.69
     intercom
    0.68
    Hand
    0.68
     množ
    0.67
    Activations Density 0.025%

    No Known Activations