© 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. 74307
    Prev
    Next
    INDEX
    Explanations

    Spring framework code

    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
     utilisés
    -1.68
     BOTH
    -1.64
    裥
    -1.58
    ཿ
    -1.55
    そうに
    -1.54
     erfaring
    -1.53
    蟶
    -1.52
    ième
    -1.52
    ໊
    -1.52
    開始
    -1.52
    POSITIVE LOGITS
     at
    2.00
     where
    1.77
     only
    1.59
     just
    1.57
     and
    1.52
     by
    1.52
     like
    1.48
     with
    1.41
     when
    1.41
     když
    1.40
    Activations Density 0.001%

    No Known Activations