© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 195167
    Prev
    Next
    INDEX
    Explanations

    statutory officer

    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
    тит
    0.48
     ignored
    0.41
    θέ
    0.40
    слу
    0.39
    Starting
    0.39
    ਿਲ
    0.38
     fidèle
    0.38
    퀄
    0.38
    ﺛ
    0.38
    Transl
    0.38
    POSITIVE LOGITS
     पीने
    0.44
     மேலும்
    0.43
    另外
    0.41
     Drinking
    0.41
     drinking
    0.40
     উপভোগ
    0.40
     ankaŭ
    0.40
     sonunda
    0.39
     roving
    0.39
     juga
    0.39
    Activations Density 0.005%

    No Known Activations