© 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. 22-GEMMASCOPE-RES-131K
    7. 98336
    Prev
    Next
    INDEX
    Explanations

    more than / something like

    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_22/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
     which
    -1.81
     in
    -1.57
     by
    -1.52
     from
    -1.46
     at
    -1.41
     we
    -1.34
     that
    -1.33
     or
    -1.26
     When
    -1.23
     修理
    -1.22
    POSITIVE LOGITS
     juger
    1.21
    ämie
    1.18
    凄い
    1.18
     keo
    1.16
    让他们
    1.11
     appliquer
    1.11
     niektórych
    1.10
    ącz
    1.10
    苼
    1.09
    긱
    1.09
    Activations Density 0.125%

    No Known Activations