© 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. 14769
    Prev
    Next
    INDEX
    Explanations

    options can be available

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

    The neuron activates on domain-specific, multi-syllable academic or technical content words (e.g. “value,” “analysis,” “stresses,” “cannot,” “obtained,” “larger”).

    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
     bukan
    -0.94
    ھ
    -0.93
    mM
    -0.90
    Alone
    -0.89
     slutt
    -0.87
     keren
    -0.86
     vaar
    -0.85
    cute
    -0.85
    ulously
    -0.84
     keer
    -0.84
    POSITIVE LOGITS
     seldom
    0.98
     than
    0.98
     progressively
    0.93
     willkommen
    0.90
     possibilities
    0.90
     rarely
    0.89
     possibility
    0.88
    同様に
    0.85
     deleteById
    0.84
    printStackTrace
    0.84
    Activations Density 0.075%

    No Known Activations