© 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. 58949
    Prev
    Next
    INDEX
    Explanations

    Linux Foundation

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

    The neuron activates on hexadecimal numeric literals (e.g. tokens making up “0x… ” sequences).

    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
     preciosas
    -1.63
     deterioro
    -1.61
    何と
    -1.52
     ayudarte
    -1.50
    ,’’
    -1.49
    ⚢
    -1.48
     colocado
    -1.48
    =="")
    -1.48
     אך
    -1.47
    又は
    -1.46
    POSITIVE LOGITS
     for
    1.90
    .
    1.68
     from
    1.39
     such
    1.34
    $,
    1.34
    寒冷
    1.30
     entonces
    1.28
     Japão
    1.28
    海外
    1.27
     in
    1.26
    Activations Density 0.005%

    No Known Activations