© 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. 22-GEMMASCOPE-RES-131K
    4. 68144
    Prev
    Next
    INDEX
    Explanations

    URLs and dates

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

    This neuron strongly activates on section headers or titles (the prominent heading lines at the start of new sections).

    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
     then
    -1.52
     but
    -1.28
     only
    -1.13
     after
    -1.00
     things
    -0.99
     on
    -0.99
     here
    -0.98
     also
    -0.97
    скими
    -0.96
    olkata
    -0.93
    POSITIVE LOGITS
    Mitä
    1.22
    eterangan
    1.13
    Tämä
    1.09
     exemplaire
    1.05
     gegebenen
    1.04
     может
    1.01
    ſtre
    0.97
    Groet
    0.96
     ahol
    0.94
     fiscales
    0.94
    Activations Density 0.137%

    No Known Activations