© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 23300
    Prev
    Next
    INDEX
    Explanations

    SWT, Win, Fill, engines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     собственно
    0.42
     aDict
    0.39
    軛
    0.39
     contralateral
    0.39
     wouldn
    0.39
     tesis
    0.38
     vattati
    0.38
     saddhim
    0.37
    Ἥ
    0.37
    footed
    0.37
    POSITIVE LOGITS
     SWT
    0.71
    SW
    0.56
     SW
    0.51
    swt
    0.48
     Moul
    0.41
     Sw
    0.40
    GC
    0.40
    ኗ
    0.40
    FormData
    0.39
     SALE
    0.39
    Activations Density 0.000%

    No Known Activations