© 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. 21597
    Prev
    Next
    INDEX
    Explanations

    glycemia, Walgreens, Ceramby, Braunschweig

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

    This neuron responds to low-frequency, domain-specific tokens—e.g. uncommon technical or medical terms, proper names, or non-English words.

    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
    t
    -3.45
     It
    -3.05
    т
    -3.00
    」　
    -2.75
    '
    -2.53
            
    -2.48
    」、
    -2.42
    .”
    -2.39
     afirmó
    -2.38
    ・・・」
    -2.38
    POSITIVE LOGITS
    uellement
    2.69
    呶
    2.66
    roleum
    2.59
    able
    2.52
    ed
    2.48
    u
    2.44
     красота
    2.42
    uttgart
    2.39
    it
    2.38
    ribune
    2.34
    Activations Density 0.161%

    No Known Activations