© 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. 96648
    Prev
    Next
    INDEX
    Explanations

    large items disposed of

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

    about anything

    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
    会导致
    0.54
     因為
    0.52
    导致
    0.50
    那时候
    0.48
     لأن
    0.48
    为
    0.47
    因为
    0.46
     Porque
    0.46
     Vì
    0.46
     ήταν
    0.45
    POSITIVE LOGITS
    mut
    0.48
    acz
    0.47
    irst
    0.47
     chops
    0.46
     IoT
    0.45
    iex
    0.45
    lek
    0.45
    蝼
    0.44
     clang
    0.44
    vie
    0.43
    Activations Density 0.003%

    No Known Activations