© 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. 237333
    Prev
    Next
    INDEX
    Explanations

    non-english languages

    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
    pot
    0.55
    Z
    0.51
    filed
    0.50
    bowl
    0.49
    Pot
    0.47
    adas
    0.46
    blank
    0.45
    colon
    0.45
    ب
    0.45
     colonized
    0.44
    POSITIVE LOGITS
     الموج
    0.50
    踰
    0.48
     แบ่ง
    0.46
     Mittwoch
    0.45
     Dienstag
    0.44
     موج
    0.44
     แรง
    0.44
    妫
    0.44
     ત્રણ
    0.43
     หมาย
    0.43
    Activations Density 0.000%

    No Known Activations