© 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. 31607
    Prev
    Next
    INDEX
    Explanations

    receive our cookies

    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
    бище
    -1.01
     it
    -0.87
     It
    -0.81
    ссию
    -0.77
    othelioma
    -0.75
     already
    -0.75
    |
    -0.72
    OptionsMenu
    -0.71
     careful
    -0.71
     ecosystems
    -0.71
    POSITIVE LOGITS
     фили
    0.87
    explained
    0.82
    Absch
    0.82
     helpt
    0.81
     ۔
    0.81
     المختلفة
    0.80
    estab
    0.79
    довые
    0.78
    planung
    0.77
    RSVP
    0.77
    Activations Density 0.003%

    No Known Activations