© 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. 106585
    Prev
    Next
    INDEX
    Explanations

    legal citation

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

    The neuron is specially tuned to pick out numeric tokens (years, dates, section numbers, citations, 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_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
     Community
    -1.02
     for
    -0.93
     ج
    -0.88
     vocal
    -0.82
     community
    -0.81
     zaměst
    -0.81
     Con
    -0.81
     article
    -0.79
     стаття
    -0.79
     com
    -0.78
    POSITIVE LOGITS
     AVAILABLE
    1.05
    Available
    1.05
     comanda
    1.02
    available
    0.99
    küche
    0.98
    vailable
    0.98
    猛地
    0.96
     disponible
    0.94
     cheia
    0.93
     Available
    0.92
    Activations Density 0.002%

    No Known Activations