© 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. 110918
    Prev
    Next
    INDEX
    Explanations

    Photo, He, Serial, <?

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

    The main thing this neuron does is detect long runs of hyphens or divider lines (as used in ASCII-style tables or charts).

    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
    \
    -1.63
     instead
    -1.39
     those
    -1.35
    Those
    -1.35
    or
    -1.27
    if
    -1.26
    i
    -1.24
     but
    -1.24
     такими
    -1.23
    //
    -1.23
    POSITIVE LOGITS
    炻
    1.84
     dégust
    1.73
     méda
    1.68
     célè
    1.63
     péro
    1.59
     mungkin
    1.56
     resalt
    1.53
     lamenta
    1.52
    땃
    1.50
     demostr
    1.48
    Activations Density 0.022%

    No Known Activations