© 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. 10376
    Prev
    Next
    INDEX
    Explanations

    rotavirus, ttf, aide

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

    file extensions and programming-related terms, particularly ".ttf" (TrueType Font) files.

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

    The neuron is picking out numeric tokens, especially floating‐point numbers (decimal values) in the text.

    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
    {
    -3.05
    ),
    -2.97
    r
    -2.63
    t
    -2.58
    ,”
    -2.55
    </h5>
    -2.42
    嚳
    -2.42
     are
    -2.41
    ).
    -2.27
    y
    -2.27
    POSITIVE LOGITS
     superiores
    2.34
    敝
    2.31
     Осно
    2.23
     stirs
    2.22
     ſou
    2.22
     خلال
    2.19
    ౮
    2.19
    廰
    2.17
     sessions
    2.16
     dangers
    2.16
    Activations Density 0.013%

    No Known Activations