© 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. 84200
    Prev
    Next
    INDEX
    Explanations

    portable toilets, type of, realized what

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

    avoid overly

    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
    0.57
    )
    0.57
     β
    0.57
     y
    0.54
     δ
    0.53
    (
    0.51
    >
    0.51
     <
    0.50
     >
    0.50
    [
    0.50
    POSITIVE LOGITS
    ಡುವುದ
    0.55
     ImageData
    0.51
    ้อม
    0.48
     InputDecoration
    0.48
    UIImage
    0.48
    羮
    0.48
    Adresse
    0.48
    沘
    0.47
     fadeInUp
    0.47
    炁
    0.47
    Activations Density 0.000%

    No Known Activations