© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 14234
    Prev
    Next
    INDEX
    Explanations

    specific compound nouns

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

    The neuron activates on the stems of multi-syllable, domain-specific technical or scientific terms (e.g. prefixes or roots of specialized nouns and adjectives).

    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
    totalPage
    -1.20
    Podob
    -1.04
    ürm
    -1.01
    jder
    -0.97
    Vlast
    -0.97
     "}";
    -0.97
     dîner
    -0.94
    ០
    -0.94
    quando
    -0.94
    música
    -0.94
    POSITIVE LOGITS
     because
    1.20
    no
    1.08
     زیرا
    1.05
     indeed
    1.02
    2
    0.96
     Additional
    0.94
    name
    0.93
     :)
    0.92
    (!
    0.92
     Indeed
    0.91
    Activations Density 0.180%

    No Known Activations