© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 8949
    Prev
    Next
    INDEX
    Explanations

    javascript module imports

    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
     landfall
    0.39
    胗
    0.39
     setae
    0.38
     elution
    0.37
    加速度
    0.37
     mtDNA
    0.36
     (°
    0.36
     kcal
    0.36
    ointing
    0.35
    全身
    0.35
    POSITIVE LOGITS
     utils
    0.48
    utils
    0.46
    Ҡ
    0.43
    工具
    0.42
    İ
    0.41
     दिग्गज
    0.41
    tools
    0.40
     playwright
    0.39
     tools
    0.39
     '../
    0.38
    Activations Density 0.012%

    No Known Activations