© 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. 70089
    Prev
    Next
    INDEX
    Explanations

    header include guards

    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
     of
    -1.98
    
    -1.75
    xspace
    -1.65
    zmm
    -1.64
    kenzo
    -1.63
    miguel
    -1.61
    fanfic
    -1.58
    yyj
    -1.56
    daun
    -1.54
    詳しくは
    -1.53
    POSITIVE LOGITS
    .
    2.41
    i
    1.86
    l
    1.70
    0
    1.69
    m
    1.63
    u
    1.56
    ↵
    1.52
    e
    1.51
    1
    1.48
    le
    1.45
    Activations Density 0.009%

    No Known Activations