© 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. 22197
    Prev
    Next
    INDEX
    Explanations

    Mandy, Hg, carton

    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
    4
    -3.59
    7
    -3.52
    6
    -3.41
    ”
    -3.36
    ”،
    -3.20
    s
    -3.17
    ″
    -2.89
    “
    -2.84
    ines
    -2.80
    。
    -2.77
    POSITIVE LOGITS
    窳
    2.72
    逦
    2.69
    してみると
    2.59
    珵
    2.58
    可以选择
    2.48
    諍
    2.48
    '
    2.34
    郸
    2.31
     conocidos
    2.30
    俥
    2.30
    Activations Density 0.006%

    No Known Activations