© 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. 99877
    Prev
    Next
    INDEX
    Explanations

    python script headers

    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
     to
    -2.03
     now
    -1.57
    '
    -1.52
     --
    -1.45
    着自己的
    -1.40
     ==
    -1.38
     Hundreds
    -1.36
    釭
    -1.35
     during
    -1.34
     looked
    -1.34
    POSITIVE LOGITS
    ↵
    1.88
    ↵↵
    1.60
    ーーーー
    1.34
     mân
    1.32
     unab
    1.31
     interesado
    1.31
    漚
    1.29
    铁路
    1.28
     râ
    1.28
    ERO
    1.27
    Activations Density 0.082%

    No Known Activations