© 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. 111158
    Prev
    Next
    INDEX
    Explanations

    office space when drawer grown ticket we

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

    switch anywhere, product generation, slightly restricted

    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
    哺
    0.52
    ບ
    0.48
    贡献
    0.47
    济
    0.47
    轮
    0.47
    刁
    0.47
    砸
    0.46
     чём
    0.45
    对
    0.45
    方便
    0.45
    POSITIVE LOGITS
    inol
    0.57
    an
    0.50
     uploaded
    0.47
     pared
    0.47
     interpolated
    0.47
     internally
    0.47
     sufficient
    0.46
     surrounded
    0.46
     progressed
    0.45
     manually
    0.45
    Activations Density 0.001%

    No Known Activations