© 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. 34-GEMMASCOPE-RES-131K
    7. 32399
    Prev
    Next
    INDEX
    Explanations

    mucosal infection

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

    code blocks with closing braces or statements followed by semicolons, particularly at the end of control structures.

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

    The neuron fires on programming‐style punctuation and delimiters—especially braces, parentheses, and semicolons.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    astet
    -0.84
     angefangen
    -0.77
    ameters
    -0.77
     aspirations
    -0.76
    oksi
    -0.75
     pulgadas
    -0.75
    geta
    -0.73
    <0xA7>
    -0.73
    BV
    -0.73
     aast
    -0.71
    POSITIVE LOGITS
     করা
    0.85
    Vors
    0.77
    Dess
    0.74
    visiae
    0.74
    edere
    0.74
     quedado
    0.73
    mogen
    0.73
    Anas
    0.73
     créer
    0.73
     سوال
    0.71
    Activations Density 0.005%

    No Known Activations