© 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. 50316
    Prev
    Next
    INDEX
    Explanations

    common phrases and international terms

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

    descriptive detail and imagery

    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
    (
    0.44
    τεύ
    0.44
    '
    0.43
    且
    0.42
    జయ
    0.42
     chapel
    0.41
    了一些
    0.41
    ὸ
    0.41
    EY
    0.41
     bou
    0.41
    POSITIVE LOGITS
    luxury
    0.46
    দানের
    0.44
     عرصے
    0.43
    awsze
    0.42
    ಡುಗೆ
    0.42
    ängen
    0.42
    ugging
    0.42
     मूल्य
    0.42
    clients
    0.42
    scht
    0.41
    Activations Density 0.000%

    No Known Activations