© 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. 99056
    Prev
    Next
    INDEX
    Explanations

    galore

    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
    ”？
    -2.50
    菝
    -2.38
     leggermente
    -2.27
    柃
    -2.20
     mago
    -2.16
    ”（
    -2.13
     hama
    -2.09
    ſam
    -2.06
    瑧
    -2.06
     thinks
    -2.00
    POSITIVE LOGITS
    ’
    3.58
    …
    2.41
    er
    2.17
    â
    1.98
    在自己
    1.88
    眼睛
    1.88
    \
    1.88
     verknüp
    1.87
     самой
    1.85
    餮
    1.85
    Activations Density 0.007%

    No Known Activations