© 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. 1790
    Prev
    Next
    INDEX
    Explanations

    request

    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
    and
    -3.14
    s
    -2.48
    い
    -2.47
    with
    -2.41
     we
    -2.25
    巨大的
    -2.16
     良
    -2.14
     naturels
    -2.13
    yled
    -2.09
    //
    -2.08
    POSITIVE LOGITS
    谖
    2.48
     nowych
    2.47
     pitiful
    2.42
    仕方
    2.39
     trabajar
    2.38
    猛然
    2.36
    giaan
    2.23
    玧
    2.20
    ⬐
    2.17
    ⇰
    2.16
    Activations Density 0.025%

    No Known Activations