© 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. 216049
    Prev
    Next
    INDEX
    Explanations

    urgent, immediate, code

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

    creative or appropriate topics

    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
    нк
    0.46
    Caf
    0.45
    convolution
    0.44
    Ȧ
    0.44
    اريخ
    0.43
     Histogram
    0.43
     établ
    0.43
    форм
    0.42
    옮
    0.42
    баров
    0.42
    POSITIVE LOGITS
     MBA
    0.46
    いや
    0.46
     industrialized
    0.44
     में
    0.43
    กับ
    0.43
    uken
    0.42
     Palestine
    0.41
     certeza
    0.41
     sequels
    0.41
     प्रतिबंधित
    0.41
    Activations Density 0.001%

    No Known Activations