© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 12257
    Prev
    Next
    INDEX
    Explanations

    simplified

    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
    <0x0D>
    0.57
    0.49
    ベーション
    0.46
    ヶ
    0.46
     बेचने
    0.42
     PYTHON
    0.42
    ה
    0.41
    པ་
    0.41
    นัก
    0.41
    Earl
    0.41
    POSITIVE LOGITS
    awed
    0.53
     hadronic
    0.49
     rumored
    0.48
    amiseks
    0.48
     mə
    0.48
    不下
    0.48
     براي
    0.46
    ल्पनिक
    0.46
     grayish
    0.43
     unorthodox
    0.43
    Activations Density 0.007%

    No Known Activations