© 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. 8532
    Prev
    Next
    INDEX
    Explanations

    mainstream [media, economists, practice]

    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
    籥
    -2.55
    馓
    -2.41
    鲞
    -2.39
     valioso
    -2.33
     Tätigkeit
    -2.30
    yym
    -2.28
     ingenieros
    -2.27
     aliados
    -2.25
     trám
    -2.25
     ก็
    -2.23
    POSITIVE LOGITS
    s
    3.64
    o
    3.38
    w
    3.28
    m
    3.23
    p
    3.13
    f
    3.06
    h
    2.89
    n
    2.89
    i
    2.66
    ”？
    2.63
    Activations Density 0.004%

    No Known Activations