© 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. 34-GEMMASCOPE-RES-131K
    7. 117700
    Prev
    Next
    INDEX
    Explanations

    managing partner or director

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

    The neuron selectively activates on numeric tokens (years, quantities, IDs) and related punctuation markers.

    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
     Escor
    -0.88
    boten
    -0.83
    temporary
    -0.76
    mengen
    -0.75
     PDC
    -0.73
     тренер
    -0.72
     آلمان
    -0.71
     mung
    -0.70
     Bhi
    -0.70
     Monto
    -0.70
    POSITIVE LOGITS
     partner
    4.16
     Partner
    3.98
    Partner
    3.64
    partner
    3.30
     partners
    3.09
     Partners
    2.63
     PARTNER
    2.52
     парт
    2.36
    Partners
    2.23
    パートナー
    2.19
    Activations Density 0.040%

    No Known Activations