© 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-262K
    4. 94046
    Prev
    Next
    INDEX
    Explanations

    like they're, polluting as, curve represents, deleting a, excels at

    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
    ८
    0.48
    一个是
    0.44
     पाये
    0.43
     аутох
    0.43
     அவர்கள்
    0.42
     extremist
    0.42
    ৭
    0.42
    퓰
    0.42
     употреб
    0.41
    CompoundButton
    0.41
    POSITIVE LOGITS
    在
    0.54
     في
    0.46
    да
    0.45
     sred
    0.44
    不上
    0.44
     in
    0.43
     mitt
    0.43
     rápido
    0.43
     thị
    0.43
     bib
    0.42
    Activations Density 0.002%

    No Known Activations