© 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. 86482
    Prev
    Next
    INDEX
    Explanations

    valor and variations

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

    The neuron activates on tokens rooted in “val” (e.g. valor, value, valued, valour, valorize).

    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
    跸
    -3.30
    櫺
    -3.22
    antaranya
    -2.97
    ları
    -2.73
    呿
    -2.67
    鳢
    -2.66
    劼
    -2.63
    欵
    -2.63
     ſch
    -2.59
     continúas
    -2.58
    POSITIVE LOGITS
     
    3.53
    2
    3.19
    2.97
    .
    2.88
    </h3>
    2.67
    If
    2.64
    In
    2.63
     Hinsicht
    2.53
    A
    2.44
     {
    2.41
    Activations Density 0.000%

    No Known Activations