© 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. 219047
    Prev
    Next
    INDEX
    Explanations

    numbers are, been working, island in

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

    wife, numerator, network, pointer

    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
    اي
    0.47
     piv
    0.46
    બ
    0.46
    лу
    0.45
    下來
    0.45
    λου
    0.44
    اريات
    0.44
    ણ
    0.43
    萆
    0.43
     Minic
    0.43
    POSITIVE LOGITS
     bowel
    0.50
     Gators
    0.50
     गौ
    0.49
    outcome
    0.48
     کودکان
    0.48
     Gator
    0.48
    type
    0.47
     hydrant
    0.46
    ⦿
    0.46
    story
    0.46
    Activations Density 0.000%

    No Known Activations