© 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. 80708
    Prev
    Next
    INDEX
    Explanations

    forming an opinion

    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
    -1.94
    with
    -1.90
     еще
    -1.75
     skriva
    -1.62
     esimer
    -1.51
     has
    -1.50
     vielä
    -1.48
     Dritte
    -1.45
     that
    -1.45
     laajenta
    -1.44
    POSITIVE LOGITS
    蚡
    1.67
     MOST
    1.60
    jaqueta
    1.56
    ESPEC
    1.44
    十分的
    1.41
     тук
    1.41
     satisfecho
    1.40
    ΄
    1.40
    AYS
    1.39
     Ρ
    1.39
    Activations Density 0.026%

    No Known Activations