© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 60030
    Prev
    Next
    INDEX
    Explanations

    expressions and lambda

    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
    完全に
    -1.50
     vux
    -1.48
    Cá
    -1.45
     reaksi
    -1.43
    尤其
    -1.40
     soutien
    -1.39
     teneur
    -1.39
     kemer
    -1.38
     others
    -1.38
     chaleur
    -1.38
    POSITIVE LOGITS
     but
    1.98
    }$.
    1.80
     și
    1.69
     We
    1.58
    liy
    1.48
    on
    1.47
     he
    1.43
    al
    1.43
     to
    1.41
    ">
    1.41
    Activations Density 0.005%

    No Known Activations