© 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. 188478
    Prev
    Next
    INDEX
    Explanations

    dental implants, Toner, coffin, familiar, signals, clasp

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

    gifts, swearing, or specific topics

    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
     કાર્યવાહી
    0.57
     ótimo
    0.46
    に行って
    0.45
    фом
    0.45
    消化
    0.45
     liệt
    0.45
     incr
    0.44
    點
    0.44
     cámaras
    0.44
     आणि
    0.43
    POSITIVE LOGITS
     Nicholson
    0.49
    ষি
    0.48
     Tonga
    0.48
     Dundee
    0.45
    nsk
    0.45
    azoo
    0.44
     Austr
    0.43
     ويت
    0.43
     Nantucket
    0.43
    বসাই
    0.42
    Activations Density 0.000%

    No Known Activations