© 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. 71826
    Prev
    Next
    INDEX
    Explanations

    business and its associates

    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
    䛗
    -2.59
    姤
    -2.55
    棪
    -2.41
    iſter
    -2.38
    伋
    -2.34
     poupée
    -2.23
     jene
    -2.23
    漚
    -2.22
    廡
    -2.19
     неболь
    -2.17
    POSITIVE LOGITS
     Also
    2.36
     teilweise
    2.28
    >
    2.25
    me
    2.22
    ↵↵
    2.13
    (\
    2.09
    怎么
    2.08
     Business
    2.08
    man
    2.03
    詫
    2.02
    Activations Density 0.009%

    No Known Activations