© 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. 102217
    Prev
    Next
    INDEX
    Explanations

    school district, can be, daily trends

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

    Shelley portrays

    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
    isierten
    0.57
     సంబంధించిన
    0.54
    ،
    0.48
     შეიძ
    0.46
    xpress
    0.46
    上述
    0.46
     ଯ
    0.46
     મા
    0.45
    ]।
    0.44
     తీసుకు
    0.43
    POSITIVE LOGITS
    ت
    0.51
    ोह
    0.50
    ر
    0.49
     Lago
    0.49
    r
    0.49
     Nair
    0.47
    Під
    0.47
    الی
    0.47
     documentación
    0.47
    Henry
    0.46
    Activations Density 0.000%

    No Known Activations