© 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. 158585
    Prev
    Next
    INDEX
    Explanations

    foreign or diverse language words

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

    truly * phrase

    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
     catalyzes
    0.52
     بادشاہ
    0.45
     catalysts
    0.44
    ريبا
    0.42
     catalyzed
    0.42
    Incidentally
    0.42
    РИ
    0.41
    ච
    0.41
    が決
    0.41
    âmb
    0.40
    POSITIVE LOGITS
     inference
    0.48
     own
    0.46
    現状
    0.45
     muse
    0.45
     earm
    0.44
    订
    0.44
     ihn
    0.43
     frågor
    0.43
     infer
    0.43
     χρήση
    0.43
    Activations Density 0.000%

    No Known Activations