© 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. 155290
    Prev
    Next
    INDEX
    Explanations

    numbers and specific codes

    np_acts-logits-general · gemini-2.5-flash-lite

    committing time, static hums, digital folklore

    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
    *
    0.50
    MAG
    0.50
    GaAs
    0.49
    <0x8C>
    0.48
    TIC
    0.48
    BEGIN
    0.47
    DAG
    0.47
    Palest
    0.47
    |
    0.47
    Islam
    0.47
    POSITIVE LOGITS
     khỏe
    0.51
     හර
    0.51
     utilice
    0.51
     പോക
    0.47
     মৌসুম
    0.46
     góc
    0.46
     Ừ
    0.46
     জার্সি
    0.46
     गर्ने
    0.45
     ẩm
    0.45
    Activations Density 0.002%

    No Known Activations