© 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. 90275
    Prev
    Next
    INDEX
    Explanations

    Kuala Lumpur and Addis Ababa

    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
    6
    -3.63
    7
    -3.59
    4
    -3.52
    3
    -3.45
    a
    -3.16
    2
    -3.09
    8
    -3.08
    5
    -3.03
    to
    -2.97
    ll
    -2.97
    POSITIVE LOGITS
    蒹
    2.70
    Ꮸ
    2.53
    袛
    2.50
     lengte
    2.44
     Lumpur
    2.44
     grünen
    2.42
    »։
    2.41
     LIBR
    2.41
    倥
    2.39
     bezoek
    2.31
    Activations Density 0.002%

    No Known Activations