© 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. 159391
    Prev
    Next
    INDEX
    Explanations

    we hope

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

    explaining the premise or purpose

    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
    эр
    0.52
    ции
    0.50
    зацию
    0.50
    ложение
    0.49
    ных
    0.49
    ాల్
    0.48
    ным
    0.48
    쫑
    0.47
    эм
    0.46
    ன்களை
    0.46
    POSITIVE LOGITS
    igram
    0.50
    ,*/}*.
    0.48
     distrib
    0.48
    ipi
    0.48
    ald
    0.47
    iena
    0.47
    pyrid
    0.45
    monte
    0.45
    wei
    0.45
    toy
    0.45
    Activations Density 0.001%

    No Known Activations