© 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. 205345
    Prev
    Next
    INDEX
    Explanations

    download, consultation, landscape

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

    temporal markers and list items

    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
     eccentric
    0.47
     hounds
    0.47
     hil
    0.45
    掑
    0.45
     resides
    0.44
     Regl
    0.44
    si
    0.44
     années
    0.43
     consp
    0.43
    atitis
    0.43
    POSITIVE LOGITS
     رسمي
    0.58
     గౌ
    0.49
     لم
    0.48
     المقسوم
    0.48
     মাহমুদ
    0.48
    ،
    0.48
     فهم
    0.48
     شراء
    0.47
     ،
    0.47
    法规
    0.47
    Activations Density 0.000%

    No Known Activations