© 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. 182456
    Prev
    Next
    INDEX
    Explanations

    foreign words or beginnings

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

    jokes involving "heard" punchlines

    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
    オフィス
    0.47
    <b>
    0.44
    ↵
    0.44
     я
    0.44
    Cruz
    0.43
     протя
    0.43
    accurate
    0.43
    ו
    0.43
    elen
    0.43
     атом
    0.42
    POSITIVE LOGITS
     voltak
    0.50
     médec
    0.47
     duas
    0.47
     अन्त
    0.45
     विविध
    0.45
     dvou
    0.45
     hendak
    0.45
     대해서
    0.44
     सरकारने
    0.44
     dibandingkan
    0.44
    Activations Density 0.000%

    No Known Activations