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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 3418
    Prev
    Next
    INDEX
    Explanations

    closing parenthesis after acronyms

    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_65k_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
    年の
    0.41
     bū
    0.40
     ブ
    0.39
     romanzo
    0.38
     دوسری
    0.37
     এমনকি
    0.37
     roky
    0.37
    ὑ
    0.37
     chữ
    0.36
     añ
    0.36
    POSITIVE LOGITS
    ecycle
    0.42
     as
    0.42
    ecology
    0.42
    in
    0.42
    ORS
    0.40
    as
    0.40
    <unused985>
    0.40
    provide
    0.38
    ders
    0.38
    at
    0.38
    Activations Density 0.073%

    No Known Activations