© 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. 181143
    Prev
    Next
    INDEX
    Explanations

    foreign words and phrases

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

    Hope, wound, caramelized, question

    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
    ี่
    0.46
    '
    0.45
    aling
    0.44
     promotion
    0.43
     शमी
    0.43
     bacterium
    0.42
    asti
    0.42
    iders
    0.40
    אל
    0.40
    ן
    0.40
    POSITIVE LOGITS
     واي
    0.51
    મારા
    0.50
    িকায়
    0.49
     исклю
    0.48
     hinted
    0.48
     különb
    0.47
     duż
    0.46
     প্রকল্পে
    0.46
     excludes
    0.46
     любых
    0.46
    Activations Density 0.000%

    No Known Activations