© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 9598
    Prev
    Next
    INDEX
    Explanations

    issue status

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

    The neuron fires on prominent post or thread status labels and metadata markers (e.g. “Closed,” “[Solved],” “Moved,” “Open,” etc.) often shown in all-caps or brackets.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     will
    -1.66
     your
    -1.55
    翆
    -1.51
     then
    -1.48
     you
    -1.47
    enuto
    -1.45
     saranno
    -1.41
    刹那
    -1.34
     serão
    -1.30
    ANNELS
    -1.28
    POSITIVE LOGITS
    or
    1.65
     by
    1.49
    which
    1.44
     and
    1.27
     a
    1.24
    on
    1.23
    m
    1.23
    .”
    1.18
    (?)
    1.16
     Optionen
    1.16
    Activations Density 0.044%

    No Known Activations