© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 102952
    Prev
    Next
    INDEX
    Explanations

    legal cases and times

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

    The neuron strongly activates on standalone headings or titles (e.g. section or document titles) rather than ordinary running text.

    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
    Poznám
    -1.23
     mostly
    -1.16
     relatively
    -1.16
     Meksi
    -1.14
     noticeable
    -1.13
     noticeably
    -1.13
     markedly
    -1.13
     vigorous
    -1.13
     mammoth
    -1.13
     meticulous
    -1.10
    POSITIVE LOGITS
    AGAIN
    1.09
    ("
    1.09
     ส
    1.07
     }}$.
    1.06
    ,"
    1.06
    ,{\
    1.05
     Dinas
    1.04
     erhi
    1.02
    ']>
    1.02
     }{
    0.99
    Activations Density 0.014%

    No Known Activations