© 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. 117982
    Prev
    Next
    INDEX
    Explanations

    chooses their, others prefer, vendors bring

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

    health assessment

    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
     Guidelines
    0.47
     Technically
    0.47
     où
    0.45
     国
    0.43
     sacer
    0.43
    中国
    0.43
     Android
    0.42
    maketitle
    0.42
    could
    0.42
     accro
    0.41
    POSITIVE LOGITS
    SERVATION
    0.52
    ockeys
    0.45
    =%
    0.45
    鹜
    0.43
     Rovers
    0.42
     bequest
    0.41
    IVEN
    0.41
    මත්
    0.41
    akat
    0.40
    perity
    0.40
    Activations Density 0.001%

    No Known Activations