© 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. 123769
    Prev
    Next
    INDEX
    Explanations

    Nic and `prevent`

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

    ellipses ("...") that indicate truncated or omitted text content.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
    !”
    -3.20
    捽
    -2.55
    鲀
    -2.52
    I
    -2.48
    ！！！”
    -2.47
    푣
    -2.44
    '
    -2.39
    $
    -2.36
    砗
    -2.33
    ܜ
    -2.33
    POSITIVE LOGITS
    a
    3.14
     has
    2.97
     builds
    2.67
     anticipates
    2.66
    ed
    2.63
     '
    2.55
     was
    2.55
    檬
    2.52
     are
    2.52
     There
    2.50
    Activations Density 0.010%

    No Known Activations