© 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. 30689
    Prev
    Next
    INDEX
    Explanations

    mode specification

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

    The neuron fires on programming identifiers—especially enum member names and other all-caps or CamelCase constants.

    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
     extracurricular
    -0.95
     zase
    -0.93
    萦
    -0.86
    tických
    -0.84
    روابط
    -0.84
     także
    -0.84
    idered
    -0.82
     friday
    -0.82
     sancti
    -0.81
     또
    -0.81
    POSITIVE LOGITS
     none
    2.09
    None
    1.80
     None
    1.80
    none
    1.66
    NONE
    1.55
     NONE
    1.46
     both
    1.36
     manual
    1.33
     nothing
    1.30
     neither
    1.30
    Activations Density 0.082%

    No Known Activations