© 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. 12089
    Prev
    Next
    INDEX
    Explanations

    leave of absence or to file

    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
     —
    -2.83
    ‘
    -2.31
    見た
    -2.03
     \
    -2.02
     utilising
    -1.99
    W
    -1.95
    .
    -1.95
     –
    -1.89
     emphas
    -1.86
    E
    -1.85
    POSITIVE LOGITS
     dichas
    2.48
    itées
    2.39
    e
    2.16
     dichos
    2.09
     tradicionales
    2.06
     soggy
    2.02
     estrictamente
    2.02
    みます
    2.02
    untuk
    2.00
     reconocido
    2.00
    Activations Density 0.004%

    No Known Activations