© 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. 32452
    Prev
    Next
    INDEX
    Explanations

    rust `mod` (`super` or `main` or `lib`)

    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
    감
    0.41
     Helvetica
    0.38
    benhav
    0.38
    aldehyde
    0.38
     베
    0.38
     என்கிறார்
    0.37
     formaldehyde
    0.37
     erop
    0.37
    ெடுக்க
    0.36
    bem
    0.36
    POSITIVE LOGITS
    நா
    0.44
    刬
    0.42
     mod
    0.41
    ::
    0.38
    ::*;
    0.38
     Mod
    0.37
    ਫ਼
    0.37
    Items
    0.36
    Picker
    0.36
     tweaking
    0.36
    Activations Density 0.002%

    No Known Activations