© 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. 167039
    Prev
    Next
    INDEX
    Explanations

    warnings.filterwarnings

    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
    Expected
    0.45
    Visible
    0.42
     क्विंट
    0.39
    護
    0.39
     хочется
    0.37
    [-\
    0.37
     interloc
    0.36
     expected
    0.36
     Drawings
    0.36
    儅
    0.36
    POSITIVE LOGITS
     Dru
    0.46
    õe
    0.43
     bele
    0.42
     sulfuric
    0.38
     vintage
    0.38
    sled
    0.38
    bele
    0.37
     silica
    0.37
     cashmere
    0.36
    ubei
    0.36
    Activations Density 0.001%

    No Known Activations