© 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. 93578
    Prev
    Next
    INDEX
    Explanations

    Q:

    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
     گیرد
    -0.71
    ajax
    -0.71
     кнопку
    -0.69
    指輪
    -0.68
    Drinks
    -0.68
     היו
    -0.68
    titleMargin
    -0.68
     rugs
    -0.68
     subsystems
    -0.68
     fibres
    -0.67
    POSITIVE LOGITS
     oscillation
    1.05
     sterile
    0.96
     oscillations
    0.93
     Oscill
    0.83
     stunted
    0.81
    PING
    0.80
     disappearance
    0.78
     Pee
    0.77
    Dm
    0.77
    oscill
    0.75
    Activations Density 0.018%

    No Known Activations