© 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. 34-GEMMASCOPE-RES-131K
    7. 30824
    Prev
    Next
    INDEX
    Explanations

    license or court

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

    The neuron primarily responds to numeric tokens (e.g. version numbers, years, report volumes, circuit identifiers) in comments and citations.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    ataly
    -0.79
     childbirth
    -0.73
    πα
    -0.72
     PERFORM
    -0.71
    SLEEP
    -0.71
     eksemp
    -0.71
    KQ
    -0.71
     trẻ
    -0.70
    atlantic
    -0.70
    イズ
    -0.69
    POSITIVE LOGITS
    ítica
    0.71
    Modific
    0.69
    Funcion
    0.66
     вересня
    0.66
    IMPORT
    0.63
     inves
    0.63
     seminar
    0.62
    nteral
    0.62
    غم
    0.61
    ۱۹
    0.60
    Activations Density 0.048%

    No Known Activations