© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 10950
    Prev
    Next
    INDEX
    Explanations

    during a time

    np_acts-logits-general · gemini-2.5-flash-lite

    happening during

    np_acts-logits-general · gemini-2.5-flash-lite

    say during

    np_max-act-logits · claude-4-5-sonnetTriggered by @skarne
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_40_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
     faute
    0.42
    DEFG
    0.34
    স্থার
    0.34
    วาม
    0.33
    ത്തിലേക്ക്
    0.33
    ੳ
    0.33
     곧
    0.32
    ír
    0.31
    కార
    0.31
    წ
    0.31
    POSITIVE LOGITS
     during
    4.09
     durante
    4.03
    during
    4.03
     DURING
    3.89
    During
    3.80
     tijdens
    3.69
     During
    3.61
     während
    3.55
     podczas
    3.50
     během
    3.39
    Activations Density 1.191%

    No Known Activations