© 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. 7665
    Prev
    Next
    INDEX
    Explanations

    $ prefix, Share, Bodging start

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

    The neuron activates on standalone numeric literals (especially decimal numbers).

    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
     $^{\
    -2.11
     imprimible
    -2.02
     nasceu
    -1.97
     encargada
    -1.87
    mhz
    -1.80
    "]=
    -1.80
     verschil
    -1.74
     isInitialized
    -1.73
    擽
    -1.72
     inalámbrico
    -1.71
    POSITIVE LOGITS
     they
    1.94
    今では
    1.74
     some
    1.68
    いただいて
    1.59
     pady
    1.57
     idée
    1.57
    畔
    1.54
    睨
    1.54
    Besos
    1.53
    悩む
    1.52
    Activations Density 0.000%

    No Known Activations