© 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. 86859
    Prev
    Next
    INDEX
    Explanations

    decreased inability estimation differential exact

    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
     when
    -2.06
     as
    -2.06
     for
    -2.03
     if
    -1.94
     but
    -1.92
     should
    -1.56
     with
    -1.55
     thing
    -1.55
     without
    -1.54
     more
    -1.45
    POSITIVE LOGITS
     pérd
    1.53
     sembla
    1.45
    ѻ
    1.44
     verlangen
    1.43
     réjou
    1.40
     échanti
    1.39
     corrom
    1.38
    knows
    1.36
     recupera
    1.36
     précédent
    1.35
    Activations Density 0.653%

    No Known Activations