© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 4415
    Prev
    Next
    INDEX
    Explanations

    tolerancy, negligence, irrigating, resect, taxicab, personalising, revegetation, ultrasonication, wristbands

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

    Accountability, recurrence, angulation

    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_53_width_65k_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
    Ils
    0.43
     kys
    0.42
     Andi
    0.42
    ጳ
    0.40
     Artem
    0.40
     garder
    0.40
     Rong
    0.39
     праздник
    0.39
     দিয়েছিল
    0.39
     kesk
    0.39
    POSITIVE LOGITS
    ifique
    0.38
    amless
    0.37
    attering
    0.37
     bhfu
    0.37
    affected
    0.37
     }^{*}$
    0.37
    piratory
    0.36
    ucidation
    0.36
    recated
    0.36
    terior
    0.36
    Activations Density 0.072%

    No Known Activations