© 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. 47701
    Prev
    Next
    INDEX
    Explanations

    closing braces and parentheses

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     of
    -1.98
    㐂
    -1.42
     eğiti
    -1.41
     rozwoju
    -1.36
    Geen
    -1.34
    Beskrivning
    -1.34
    来週
    -1.33
     rencont
    -1.33
    e
    -1.31
     详情
    -1.30
    POSITIVE LOGITS
     you
    1.57
     suoi
    1.52
    袂
    1.49
     colocando
    1.48
     /\.
    1.47
     its
    1.42
    "../
    1.41
    ESTONE
    1.36
    اتها
    1.35
     vrea
    1.33
    Activations Density 0.026%

    No Known Activations