© 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. 121780
    Prev
    Next
    INDEX
    Explanations

    oral cholera vaccine

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

    whyit's

    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
    铁路
    0.57
     巴
    0.54
     pó
    0.52
    推广
    0.52
     बट
    0.51
    区间
    0.50
    僌
    0.50
    𝚙
    0.50
    暂时
    0.50
    血压
    0.50
    POSITIVE LOGITS
    the
    0.50
    WARE
    0.47
    6
    0.47
    THE
    0.45
    5
    0.44
    CO
    0.44
     false
    0.43
     the
    0.42
     />
    0.42
    is
    0.41
    Activations Density 0.000%

    No Known Activations