© 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. 222889
    Prev
    Next
    INDEX
    Explanations

    shadows and shadows

    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
    row
    0.45
    Pray
    0.41
     NN
    0.40
    杏
    0.40
    _),
    0.39
     MND
    0.38
     ál
    0.38
    નેસ
    0.37
    )>=
    0.37
    ाम
    0.37
    POSITIVE LOGITS
     Shadows
    0.44
     ফর্ম
    0.41
     Cách
    0.40
     shadow
    0.40
     shadowing
    0.39
     ადამიან
    0.38
     Schatten
    0.38
     cub
    0.38
     sabot
    0.38
     shadows
    0.37
    Activations Density 0.000%

    No Known Activations