© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 40488
    Prev
    Next
    INDEX
    Explanations

    code structure and formatting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    dataset
    0.43
     altre
    0.43
     କରି
    0.42
    ⚠️
    0.42
    filePath
    0.42
     কথাও
    0.42
    夎
    0.42
     মস্তি
    0.41
    dataFile
    0.41
    🦞
    0.41
    POSITIVE LOGITS
    ای
    0.45
     resolving
    0.44
     Townsend
    0.44
     قسم
    0.42
     maximus
    0.42
    ak
    0.41
     shipbuilding
    0.41
    ные
    0.41
     রয়েছে
    0.41
     subsections
    0.41
    Activations Density 0.000%

    No Known Activations