© 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. 71305
    Prev
    Next
    INDEX
    Explanations

    code and download progress

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

    The neuron fires on occurrences of code file extensions (e.g. “.html”, “.js”) or filenames, spotting mentions of HTML/JS files.

    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
     '
    -2.02
     -
    -1.71
     cuando
    -1.64
     suele
    -1.63
     and
    -1.58
    '.
    -1.58
     mientras
    -1.53
     --
    -1.52
     estaba
    -1.52
     aparece
    -1.49
    POSITIVE LOGITS
    鷓
    2.08
    塤
    2.00
    嫆
    1.98
    媄
    1.98
    𓆜
    1.91
    浤
    1.84
    来
    1.81
    蛔
    1.81
    古风
    1.80
    miento
    1.79
    Activations Density 0.069%

    No Known Activations