© 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. 161623
    Prev
    Next
    INDEX
    Explanations

    village hall, first ever

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

    causal influences

    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
     +-
    0.48
     或
    0.47
     warto
    0.47
     但
    0.46
     XY
    0.45
    或
    0.45
     GHz
    0.44
     lunar
    0.44
     Vý
    0.44
    POSITIVE LOGITS
    ا
    0.50
    दिया
    0.49
    etheus
    0.47
    sockets
    0.47
    deals
    0.47
    soc
    0.47
    gak
    0.47
    اك
    0.46
    ச்சே
    0.46
    encript
    0.46
    Activations Density 0.000%

    No Known Activations