© 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. 58444
    Prev
    Next
    INDEX
    Explanations

    business growth

    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
     vuestro
    -1.69
    酲
    -1.64
     オン
    -1.61
    俛
    -1.59
     vostro
    -1.57
    ≧
    -1.53
     trast
    -1.53
    慙
    -1.50
     ハート
    -1.49
    Seperti
    -1.48
    POSITIVE LOGITS
    他们的
    1.80
     of
    1.66
    她的
    1.63
    4
    1.61
     ihre
    1.60
     einfach
    1.59
    他的
    1.52
     kişilik
    1.47
     brauche
    1.45
    我们的
    1.43
    Activations Density 0.016%

    No Known Activations