© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 27785
    Prev
    Next
    INDEX
    Explanations

    Q before colon

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

    The neuron detects tokens that are part of formal organization or certification authority names (e.g. “American,” “Society,” “Association,” “Commission,” etc.).

    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
     ventajas
    -1.37
     Ofrece
    -1.28
     that
    -1.28
     actualizaciones
    -1.19
     vantagens
    -1.17
     ervaren
    -1.16
     configurações
    -1.16
    pushFollow
    -1.16
     definiciones
    -1.16
     חיצוני
    -1.15
    POSITIVE LOGITS
     作り方
    1.09
     screenWidth
    1.05
    TECN
    1.05
     convers
    0.99
    tualmente
    0.99
    ativen
    0.98
    Beskrivning
    0.98
     جایی
    0.98
     américa
    0.97
    Vand
    0.96
    Activations Density 0.015%

    No Known Activations