© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 119835
    Prev
    Next
    INDEX
    Explanations

    Ways to, On Air, Scholars Differ

    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
    ↵
    -3.05
    鬟
    -2.81
    '),
    -2.69
     They
    -2.59
     hicieron
    -2.52
     fueran
    -2.48
     ayudado
    -2.47
     or
    -2.44
     â
    -2.44
     zarówno
    -2.41
    POSITIVE LOGITS
    A
    3.03
    \
    3.03
    O
    2.86
    E
    2.59
     sebagainya
    2.45
    C
    2.38
    $
    2.34
    秾
    2.34
    _
    2.31
    ING
    2.13
    Activations Density 0.000%

    No Known Activations