© 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. 183948
    Prev
    Next
    INDEX
    Explanations

    "ABC talk" or "hire vehicle"

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

    bath bombs

    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
    दायिक
    0.43
    Người
    0.42
    횃
    0.42
     जिंक
    0.42
    小
    0.41
    Wear
    0.41
    Photo
    0.41
    ধিক
    0.41
    、
    0.41
    লিত
    0.40
    POSITIVE LOGITS
    ሞ
    0.50
    ंपेक्षा
    0.48
     projek
    0.48
     similaires
    0.47
    ati
    0.47
     کن
    0.46
     serupa
    0.46
     similaire
    0.45
    लोड
    0.45
    nada
    0.44
    Activations Density 0.001%

    No Known Activations