© 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. 15299
    Prev
    Next
    INDEX
    Explanations

    software

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

    The neuron consistently fires on the word “software,” especially in license or documentation headers.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     
    -2.94
     The
    -2.16
     '
    -2.11
    '
    -2.11
     \
    -2.09
    锇
    -2.06
     On
    -2.05
     sosok
    -2.03
    ‘
    -1.95
    嫱
    -1.91
    POSITIVE LOGITS
    媖
    3.00
    镚
    2.64
    In
    2.63
    The
    2.56
    」
    2.56
    .
    2.52
    </h3>
    2.38
    鉭
    2.33
    ztes
    2.27
    ジナル
    2.25
    Activations Density 0.041%

    No Known Activations