© 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. 7120
    Prev
    Next
    INDEX
    Explanations

    printf statements

    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
     должна
    -1.77
    首先
    -1.63
    两个
    -1.62
    醞
    -1.62
    From
    -1.57
    If
    -1.48
    她们
    -1.47
    應該
    -1.45
     тільки
    -1.45
     then
    -1.42
    POSITIVE LOGITS
     but
    1.56
     managing
    1.39
    了的
    1.38
    coledì
    1.37
    䨻
    1.36
     today
    1.34
    Ability
    1.32
    izedBox
    1.32
    itato
    1.31
    ätigung
    1.30
    Activations Density 0.002%

    No Known Activations