© 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
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 111747
    Prev
    Next
    INDEX
    Explanations

    arising out of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sonunda
    0.43
    dü
    0.43
     کاسینو
    0.43
     élytres
    0.43
    స్ట్రీ
    0.43
    Ě
    0.42
    ⺆
    0.41
     जिलों
    0.41
     préférable
    0.40
     रस्त
    0.40
    POSITIVE LOGITS
    言
    0.41
     поле
    0.39
     associations
    0.38
     association
    0.37
    kot
    0.37
    association
    0.37
    Saint
    0.35
    ignor
    0.35
    ucid
    0.35
    adari
    0.35
    Activations Density 0.000%

    No Known Activations