© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 128645
    Prev
    Next
    INDEX
    Explanations

    broad, local, simple, or neighboring

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mesons
    0.55
     dioxide
    0.52
     によって
    0.47
     による
    0.44
     verkl
    0.44
     Dioxide
    0.43
    ா
    0.42
     年
    0.42
     Negara
    0.41
     destes
    0.41
    POSITIVE LOGITS
    Cultural
    0.46
     unassuming
    0.46
    ಬ್ಬಳ್ಳಿ
    0.45
    Getting
    0.45
    Becoming
    0.44
    ശു
    0.44
    Пер
    0.44
     बुनियादी
    0.43
     humbled
    0.43
    തി
    0.43
    Activations Density 0.011%

    No Known Activations