© 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. 8009
    Prev
    Next
    INDEX
    Explanations

    inside, between, by, into, of the

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

    individual cells

    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
    之时
    0.76
    财政
    0.71
    职位
    0.69
    经纪
    0.69
    骄
    0.68
    喜剧
    0.67
    赚钱
    0.66
    骗
    0.66
     जाहीर
    0.66
    书记
    0.65
    POSITIVE LOGITS
     surface
    0.77
     convective
    0.75
     thermal
    0.75
     cylindrical
    0.75
     layer
    0.74
     submerged
    0.74
     trapped
    0.73
     fibrous
    0.72
     compacted
    0.72
     thermally
    0.71
    Activations Density 0.058%

    No Known Activations