© 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. 88626
    Prev
    Next
    INDEX
    Explanations

    negotiations, complaint, indicator, 貓, critics, candidate

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

    seeing significant change

    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
    กอง
    0.52
    غ
    0.49
    อน
    0.47
    aganda
    0.47
    กรม
    0.47
    Gall
    0.46
    Madonna
    0.46
    活
    0.45
    ㈡
    0.45
    ังก
    0.45
    POSITIVE LOGITS
     ຫຼື
    0.52
    <unused6>
    0.49
     выполнять
    0.49
     کوډ
    0.48
     calef
    0.48
     utwor
    0.47
    ຫຼື
    0.46
     kaldır
    0.46
     założ
    0.45
    radial
    0.44
    Activations Density 0.000%

    No Known Activations