© 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. 94643
    Prev
    Next
    INDEX
    Explanations

    waste disposal, family, and nature

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

    customer complaint dispute

    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
    lessly
    0.51
    vamente
    0.50
    NGTH
    0.49
    ำ
    0.48
    ８
    0.47
    шается
    0.46
    杆
    0.46
     안녕하세요
    0.46
    ರ
    0.46
    在
    0.46
    POSITIVE LOGITS
     couture
    0.51
     costume
    0.51
     sawmill
    0.49
     crise
    0.48
     outage
    0.47
     saw
    0.46
     licences
    0.46
     bourse
    0.46
     recess
    0.46
     customised
    0.45
    Activations Density 0.002%

    No Known Activations