© 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. 216721
    Prev
    Next
    INDEX
    Explanations

    environmentally safe

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

    function close()

    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
    ন
    0.50
     refrained
    0.49
     cobre
    0.48
    boh
    0.47
    ('=
    0.45
     футболдук
    0.45
     nenhuma
    0.44
     инфра
    0.44
     جین
    0.43
     말투
    0.43
    POSITIVE LOGITS
     funerals
    0.46
     polling
    0.45
     Television
    0.44
     racing
    0.42
     Exposure
    0.42
     exposure
    0.41
     ছুর
    0.41
    ’
    0.41
    應該
    0.40
     uprising
    0.40
    Activations Density 0.000%

    No Known Activations