© 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. 75828
    Prev
    Next
    INDEX
    Explanations

    ready to spare

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

    steam mop

    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
    グッズ
    0.49
     ד
    0.47
    یکا
    0.46
     Geç
    0.45
     ی
    0.45
    وسف
    0.45
     سین
    0.44
     Lef
    0.44
    妽
    0.44
     Sven
    0.43
    POSITIVE LOGITS
    l
    0.47
    ind
    0.46
    college
    0.46
    kings
    0.45
     religión
    0.45
     जिस
    0.44
     biodiversity
    0.44
    globe
    0.44
     cartel
    0.43
    oy
    0.42
    Activations Density 0.000%

    No Known Activations