© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 192428
    Prev
    Next
    INDEX
    Explanations

    profit, inclined, more

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

    but, in, into, too

    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
    Negative Logits
     ক্ষত
    0.49
    PostMapping
    0.48
     kain
    0.46
    他们的
    0.45
    kräft
    0.44
     membrana
    0.44
    ụt
    0.44
    क्षिक
    0.44
    )}-\
    0.43
     पद्म
    0.43
    POSITIVE LOGITS
    or
    0.61
    on
    0.49
    ell
    0.44
     বাঙ্গালা
    0.44
    leness
    0.44
     deliberation
    0.43
    op
    0.43
    penalty
    0.42
    មូល
    0.42
     diligence
    0.41
    Activations Density 0.002%

    No Known Activations