© 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. 27866
    Prev
    Next
    INDEX
    Explanations

    phrases after conjunctions or punctuation

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

    phrases for reconstruction or crisis

    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
     newborns
    0.41
    niejszych
    0.41
    жай
    0.40
    높
    0.40
    जन्म
    0.40
    utilise
    0.39
     Грузии
    0.39
    niejsze
    0.39
     разрешения
    0.39
     البد
    0.39
    POSITIVE LOGITS
     ello
    0.45
     (
    0.42
     equilibrated
    0.41
     Cred
    0.41
    网页
    0.41
     tedy
    0.40
    也就是说
    0.40
    说道
    0.39
    ುದು
    0.39
     pdf
    0.39
    Activations Density 0.000%

    No Known Activations