© 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
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 125923
    Prev
    Next
    INDEX
    Explanations

    carve path, summoner, call follow-up, wave puzzle

    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
    पीड़न
    0.51
    ሳሪያ
    0.50
    संस्करण
    0.43
     evocative
    0.42
    ार्मिक
    0.41
     proporcionan
    0.41
    ావ
    0.40
    ✨
    0.40
    긁
    0.40
     tamaño
    0.40
    POSITIVE LOGITS
     людини
    0.46
     الحمد
    0.44
    <0xE3>
    0.43
    strs
    0.43
    </
    0.43
    lvl
    0.42
    ्हे
    0.42
     الجما
    0.42
     फेड
    0.42
    ($
    0.42
    Activations Density 0.003%

    No Known Activations