© 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. 129392
    Prev
    Next
    INDEX
    Explanations

    The neuron is keyed to technical, domain‐specific terms (e.g. specialized nouns in scientific, medical, patent, or mathematical contexts).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    scientific and technical analysis

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    </em>
    -1.09
     بشأن
    -0.95
    Unmount
    -0.90
    Šaltiniai
    -0.88
    jando
    -0.85
    ///////////
    -0.84
    fl
    -0.84
    -0.84
    trust
    -0.84
     />";
    -0.84
    POSITIVE LOGITS
    甬
    1.05
     DELLA
    0.96
    epam
    0.94
    Estr
    0.92
    ෛ
    0.92
    ニム
    0.90
    がっ
    0.90
    brazilian
    0.89
    跗
    0.88
    :///
    0.88
    Activations Density 0.084%

    No Known Activations