© 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. 40229
    Prev
    Next
    INDEX
    Explanations

    variations of none

    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
    leggio
    -2.73
    但我
    -2.73
    但这
    -2.66
     Partly
    -2.53
    ဴ
    -2.45
    ulico
    -2.30
     strongest
    -2.30
     annoy
    -2.28
    ENCIL
    -2.27
     Former
    -2.25
    POSITIVE LOGITS
    歺
    2.92
    место
    2.47
     láp
    2.38
    苼
    2.38
    部分が
    2.33
    湏
    2.31
    一旁
    2.28
     dage
    2.25
    ientras
    2.25
    ludes
    2.22
    Activations Density 0.001%

    No Known Activations