© 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. 33180
    Prev
    Next
    INDEX
    Explanations

    comparisons, degree, likeness

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

    The neuron fires on longer, multi-syllable content words—especially technical or domain-specific terms.

    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
     boute
    -1.05
    هذه
    -0.98
    뀐
    -0.93
    ⃤
    -0.93
    على
    -0.92
     bapt
    -0.92
    ıntı
    -0.91
     onderdelen
    -0.90
    ആ
    -0.89
     FORD
    -0.89
    POSITIVE LOGITS
     closer
    1.50
     more
    1.48
     nearer
    1.18
     our
    1.15
    Closer
    1.08
     rather
    1.08
    มากกว่า
    1.08
     but
    1.02
     بیشتر
    1.01
     Closer
    1.00
    Activations Density 0.033%

    No Known Activations