© 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. 22-GEMMASCOPE-RES-131K
    7. 27645
    Prev
    Next
    INDEX
    Explanations

    code and comments

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

    This neuron responds to numeric literals in code (i.e. sequences of digits, with or without decimal points).

    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
     of
    -1.17
     What
    -1.09
     what
    -1.08
    hoten
    -1.03
     its
    -1.03
    cxt
    -1.02
    what
    -1.02
     Their
    -0.98
    ాలు
    -0.98
    vky
    -0.96
    POSITIVE LOGITS
     durabilidad
    1.10
     prestaciones
    1.07
     będę
    1.06
     funcionamento
    1.02
     plazos
    1.02
     やすい
    1.02
     zawsze
    1.01
    materialien
    1.01
    也可以
    1.00
    loß
    1.00
    Activations Density 0.038%

    No Known Activations