© 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. 68808
    Prev
    Next
    INDEX
    Explanations

    recent news

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

    The neuron doesn’t reliably activate on any of the shown text—it appears to be effectively dormant.

    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
     is
    -1.49
    ʙ
    -1.32
    ल
    -1.32
    Still
    -1.28
    wickshire
    -1.25
    ISSIPPI
    -1.25
     didn
    -1.24
    So
    -1.23
    erda
    -1.23
    дела
    -1.23
    POSITIVE LOGITS
     besoins
    1.24
    Okey
    1.21
     различ
    1.19
     Their
    1.16
     any
    1.15
    Fourni
    1.15
    嚒
    1.15
     formules
    1.13
    AMAZING
    1.13
    ㌘
    1.12
    Activations Density 0.010%

    No Known Activations