© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 16132
    Prev
    Next
    INDEX
    Explanations

    obtaining contacts

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

    The neuron fires strongly on very common, high‐frequency tokens—chiefly function words (prepositions, articles, auxiliary verbs) and frequent punctuation.

    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
     etap
    -1.03
    Beantwoorden
    -1.03
    __((
    -0.96
    icts
    -0.96
     telah
    -0.95
    weis
    -0.89
    Reve
    -0.89
    Ĩ
    -0.88
    cún
    -0.87
    vides
    -0.86
    POSITIVE LOGITS
     auprès
    1.48
     through
    1.38
     obtaining
    1.19
     contacts
    1.13
     affinch
    1.11
     with
    1.09
     obtain
    1.05
     contacting
    1.04
    も良い
    1.03
    獲得
    1.02
    Activations Density 0.029%

    No Known Activations