© 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. 165002
    Prev
    Next
    INDEX
    Explanations

    fuel efficiency

    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
     vicepresidente
    0.39
    떴
    0.39
     bicovariant
    0.38
     seedlings
    0.38
     precursors
    0.38
    序号
    0.38
    ('$
    0.37
    ┈┈
    0.37
    ˹
    0.37
     prognostic
    0.37
    POSITIVE LOGITS
     Fourteen
    0.38
     cheval
    0.37
    anç
    0.37
    principal
    0.37
     none
    0.36
    ığın
    0.36
    Principal
    0.35
     சேர்த்த
    0.35
    ensional
    0.35
     لذ
    0.35
    Activations Density 0.000%

    No Known Activations