© 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. 34-GEMMASCOPE-RES-131K
    7. 76759
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols

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

    The neuron flags content‐bearing, information‐rich tokens (uncommon nouns, proper names, technical terms, and other semantically heavy words).

    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
    renaline
    -1.00
    orable
    -0.94
     documentación
    -0.93
     générations
    -0.93
     EQUAL
    -0.91
    always
    -0.90
    accessed
    -0.89
    brtc
    -0.87
     trabajador
    -0.87
    providing
    -0.85
    POSITIVE LOGITS
     nine
    1.43
     five
    1.25
     three
    1.21
     seven
    1.20
     six
    1.19
     eight
    1.18
     four
    1.14
     twelve
    1.04
     exquisite
    1.02
     two
    0.98
    Activations Density 0.004%

    No Known Activations