© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 113464
    Prev
    Next
    INDEX
    Explanations

    uncertainty relation or region

    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
    genodigd
    -2.73
     nemico
    -2.73
    ㍑
    -2.66
    苤
    -2.64
     enraged
    -2.63
    afbeelding
    -2.58
     importanza
    -2.55
    甞
    -2.53
    という
    -2.50
     vostro
    -2.50
    POSITIVE LOGITS
    .
    2.86
    $
    2.55
    ↵↵
    2.33
    ↵
    2.28
    tably
    2.14
    籐
    2.13
     of
    2.08
    嫘
    2.06
    th
    2.05
    !)
    2.05
    Activations Density 0.003%

    No Known Activations