© 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. 10-GEMMASCOPE-RES-131K
    7. 99756
    Prev
    Next
    INDEX
    Explanations

    `Generated` or `attachment`

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

    The neuron fires on very short, single‐character tokens—letters or digits.

    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
     対策
    -1.28
    ituksen
    -1.26
     engaging
    -1.25
    It
    -1.23
     anarchy
    -1.23
     плану
    -1.20
     serpentine
    -1.20
     購入
    -1.19
     種類
    -1.18
     entailed
    -1.16
    POSITIVE LOGITS
    轳
    1.49
     ۱۰
    1.45
            
    1.45
     escribiendo
    1.41
     ofreciendo
    1.41
     destacados
    1.36
     cielos
    1.34
     dream
    1.34
     ł
    1.31
     Hà
    1.31
    Activations Density 0.001%

    No Known Activations