© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 193466
    Prev
    Next
    INDEX
    Explanations

    without departing

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

    use for routing, stood before, check status

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
     automatis
    0.60
    了一些
    0.57
     sara
    0.49
    知道
    0.48
    ّة
    0.48
     rask
    0.48
    ré
    0.47
    懺
    0.47
     spä
    0.46
     impul
    0.46
    POSITIVE LOGITS
    fromi
    0.47
    ాన్
    0.45
     நிகழ்
    0.44
     বীর
    0.44
     ஸ்ட
    0.44
    bodied
    0.44
     민
    0.43
     Peny
    0.43
    fromParams
    0.43
     تړل
    0.42
    Activations Density 0.000%

    No Known Activations