© 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. 87245
    Prev
    Next
    INDEX
    Explanations

    necessary, required, desired items

    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
     of
    -3.20
     in
    -2.27
     tohoto
    -1.82
     to
    -1.80
     Besonder
    -1.77
     belangrijk
    -1.76
     Национа
    -1.76
    etsk
    -1.75
    geable
    -1.70
     podpor
    -1.69
    POSITIVE LOGITS
    "
    2.39
    '
    2.19
     —
    2.13
     moteurs
    2.00
     kablo
    1.90
     toalha
    1.86
    先日
    1.77
    「
    1.77
     Infir
    1.73
     bougies
    1.72
    Activations Density 0.096%

    No Known Activations