© 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. 10-GEMMASCOPE-RES-131K
    7. 38732
    Prev
    Next
    INDEX
    Explanations

    FIG. 1 followed by description

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

    This neuron detects occurrences of figure reference labels, e.g. “FIG. 1.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     лишь
    -2.09
    }
    -1.80
    на
    -1.79
    innerWidth
    -1.79
    LETIN
    -1.78
    Surprisingly
    -1.76
    دي
    -1.75
    ”,
    -1.70
     noteworthy
    -1.70
    ⸂
    -1.63
    POSITIVE LOGITS
    feste
    1.86
     sám
    1.81
    ︓
    1.71
     expliqué
    1.71
    archiwizowane
    1.65
     parede
    1.65
     because
    1.63
    klassi
    1.62
    gruppen
    1.61
    ಼
    1.61
    Activations Density 0.008%

    No Known Activations