© 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. 15307
    Prev
    Next
    INDEX
    Explanations

    samples, groups, species, agents, materials

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

    The neuron identifies plural nouns and noun phrases, particularly in scientific research contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron fires on numeric data tokens (quantities, measurements, counts, percentages, etc.) in scientific text.

    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
     and
    -1.02
     pakket
    -1.00
    おそ
    -0.96
     tirantes
    -0.95
    TIPOS
    -0.95
     sterke
    -0.93
     pagină
    -0.93
    seguro
    -0.93
     białe
    -0.93
     estremamente
    -0.92
    POSITIVE LOGITS
    детская
    1.21
    ichthys
    1.08
     més
    1.04
    Anche
    0.95
    間
    0.92
    ╦
    0.92
    Géographie
    0.90
     ficou
    0.89
    erdings
    0.89
     algún
    0.88
    Activations Density 0.050%

    No Known Activations