© 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. 56009
    Prev
    Next
    INDEX
    Explanations

    dates and locations

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

    words followed by common words

    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
     food
    0.52
     FOOD
    0.52
    т
    0.48
     radiance
    0.48
     SHOP
    0.47
     wheat
    0.47
    素敵
    0.47
    ت
    0.46
    efficiency
    0.46
     Himself
    0.46
    POSITIVE LOGITS
    fax
    0.50
    Officials
    0.44
    mäßig
    0.44
    רית
    0.43
    Prove
    0.43
    ículo
    0.42
     nyeri
    0.42
     الاكس
    0.41
    mateurs
    0.41
     bizarre
    0.41
    Activations Density 0.000%

    No Known Activations