© 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. 110594
    Prev
    Next
    INDEX
    Explanations

    names followed by a comma and description

    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
    、
    -1.09
    Vendo
    -1.09
    b
    -1.05
     werde
    -1.04
     ikke
    -1.04
    tive
    -1.04
    место
    -1.03
    c
    -1.03
     bukan
    -1.02
     anderes
    -1.02
    POSITIVE LOGITS
    ooplankton
    1.23
    llingwood
    1.17
    ה
    1.16
    ('');
    1.13
     establecidos
    1.11
    スコット
    1.09
     frequented
    1.07
     discounting
    1.07
    Xiv
    1.06
    kannten
    1.06
    Activations Density 0.067%

    No Known Activations