© 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. 22-GEMMASCOPE-RES-131K
    7. 79904
    Prev
    Next
    INDEX
    Explanations

    description or parameters

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

    The neuron activates on Markdown/YAML section markers—lines beginning with “#”, “##”, etc., or the “---” separators.

    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
     mármol
    -1.23
     besonder
    -1.16
     everyone
    -1.16
     now
    -1.13
     órganos
    -1.13
     новом
    -1.13
     Lösungs
    -1.11
     nobody
    -1.09
     ใช้
    -1.08
     deberes
    -1.08
    POSITIVE LOGITS
     純正
    1.16
    carus
    1.09
    However
    1.07
    ’
    1.06
     FOLLOW
    1.04
    -
    1.04
    糯米
    1.01
    (;
    1.00
     حسب
    0.98
    le
    0.98
    Activations Density 0.003%

    No Known Activations