© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 58129
    Prev
    Next
    INDEX
    Explanations

    PUBLIC -

    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_34/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
    死亡
    -0.75
    <&
    -0.75
     quedó
    -0.74
     tái
    -0.70
     ಬ
    -0.70
    Obrázky
    -0.70
    PAGE
    -0.69
    qed
    -0.69
     fixed
    -0.68
     giocatori
    -0.68
    POSITIVE LOGITS
     Darfur
    0.65
    ensk
    0.64
    services
    0.61
     ਅ
    0.61
    exus
    0.60
     Speakers
    0.60
     услуги
    0.60
     Levi
    0.59
     Caval
    0.59
     starry
    0.59
    Activations Density 0.063%

    No Known Activations