© 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. 40-GEMMASCOPE-2-RES-16K
    7. 8752
    Prev
    Next
    INDEX
    Explanations

    markdown table separators

    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_40_width_16k_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
    衅
    0.40
    အစိတ်အပိုင်း
    0.40
    Corners
    0.40
    ButtonPressed
    0.39
     prefer
    0.39
    贴
    0.39
    اديه
    0.39
    岘
    0.39
    ادری
    0.38
    YL
    0.38
    POSITIVE LOGITS
    cline
    0.56
    hline
    0.43
    midrule
    0.39
    ਜ
    0.38
     Quel
    0.38
     {})
    0.38
     Australia
    0.38
     Vamp
    0.37
     *)&
    0.37
    solete
    0.37
    Activations Density 0.076%

    No Known Activations