© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 4551
    Prev
    Next
    INDEX
    Explanations

    core concepts and basics

    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
     accomplishes
    0.31
    Voici
    0.30
     которые
    0.29
    騾
    0.29
     misconceptions
    0.29
    le
    0.29
    ことを
    0.29
    ene
    0.29
    sene
    0.28
    <unused1079>
    0.28
    POSITIVE LOGITS
     Mesmo
    0.34
    atorio
    0.32
     auß
    0.32
     Kitty
    0.31
     이거
    0.31
    叧
    0.30
     titulares
    0.30
    tained
    0.30
    之内
    0.30
    ంబ
    0.29
    Activations Density 0.116%

    No Known Activations