© 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. 112125
    Prev
    Next
    INDEX
    Explanations

    names and foreign words

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

    exclamations and specific nouns

    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
    맇
    0.52
     QSOs
    0.50
     использовали
    0.47
    returnValue
    0.46
    たす
    0.46
     localize
    0.45
     subcl
    0.45
    ර
    0.44
    ದ್ರ
    0.44
    ವಿದೆ
    0.44
    POSITIVE LOGITS
     Georg
    0.46
     Captain
    0.44
     Hungarian
    0.44
     samarbe
    0.43
     माउंट
    0.43
     Gods
    0.42
     সিনে
    0.42
     Джей
    0.42
     Cumberland
    0.42
    Georg
    0.42
    Activations Density 0.000%

    No Known Activations