© 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. 34430
    Prev
    Next
    INDEX
    Explanations

    comparative or transitional words

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

    The neuron spotlights numeric threshold expressions and comparative markers (e.g. “above,” “below,” “longer than”) in measurements.

    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
    sturm
    -0.84
     phénomène
    -0.82
     paysage
    -0.82
    卡通
    -0.82
    ăzi
    -0.81
    ixas
    -0.81
    水墨
    -0.80
    ísimas
    -0.80
     ngayon
    -0.79
     comportement
    -0.79
    POSITIVE LOGITS
     but
    4.44
     nhưng
    2.61
    but
    2.42
     אך
    2.41
     แต่
    2.19
     लेकिन
    2.17
     αλλά
    1.99
     ولی
    1.96
     tetapi
    1.93
     ولكن
    1.92
    Activations Density 0.101%

    No Known Activations