© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 11609
    Prev
    Next
    INDEX
    Explanations

    loop function calls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ч
    1.93
     Séance
    1.92
     (°
    1.85
     ا
    1.80
     เอ
    1.80
     Ꭰ
    1.75
     เอา
    1.75
     池
    1.73
     coincident
    1.72
    Ч
    1.72
    POSITIVE LOGITS
    quality
    1.45
    abling
    1.38
    män
    1.34
     quality
    1.33
    cere
    1.29
    ivering
    1.28
    bmi
    1.25
     ontwikkel
    1.23
     calidad
    1.23
    significant
    1.23
    Activations Density 0.000%

    No Known Activations