© 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. 10-GEMMASCOPE-RES-131K
    7. 103485
    Prev
    Next
    INDEX
    Explanations

    code snippets

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

    leading whitespace or indentation at the beginning of lines in code.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron is detecting numeric literals (sequences of digits) in code.

    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
     '
    -1.34
    にします
    -1.32
    能否
    -1.30
     piaci
    -1.29
     estric
    -1.29
    といって
    -1.27
     related
    -1.27
     and
    -1.25
     -
    -1.24
    まさかの
    -1.24
    POSITIVE LOGITS
     '/';
    1.59
     it
    1.50
    vább
    1.34
    riwal
    1.32
    詬
    1.31
    pography
    1.30
     CHARACTERS
    1.30
    🤤
    1.24
    🤭
    1.23
    🧡
    1.22
    Activations Density 0.017%

    No Known Activations