© 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. 139885
    Prev
    Next
    INDEX
    Explanations

    sentence starter after period

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

    they are effectively improving

    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
    ოტ
    0.47
    өм
    0.46
    switching
    0.45
    hol
    0.44
    unsch
    0.44
     constraining
    0.44
    ын
    0.43
    ängt
    0.43
    <0x9F>
    0.42
     leasing
    0.42
    POSITIVE LOGITS
    সমান
    0.47
    BackColor
    0.47
     DefaultTargets
    0.43
     Urology
    0.40
    汜
    0.40
     ceva
    0.39
    甚至
    0.39
     কাহিনী
    0.39
     Requires
    0.38
    一口
    0.38
    Activations Density 0.001%

    No Known Activations