© 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. 43768
    Prev
    Next
    INDEX
    Explanations

    booking tickets

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

    economic, Flights, RSI, risk, Speech

    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
     watcher
    0.51
    ากหลาย
    0.50
    balik
    0.49
    さが
    0.48
    わた
    0.47
    ワ
    0.47
     WORTH
    0.46
    اتب
    0.46
    цэ
    0.46
    ็ง
    0.44
    POSITIVE LOGITS
     If
    0.54
     Box
    0.52
    ine
    0.52
     It
    0.51
     Mount
    0.51
     Mounting
    0.50
     Having
    0.49
     Detailed
    0.49
     I
    0.49
     On
    0.47
    Activations Density 0.000%

    No Known Activations