© 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. 40-GEMMASCOPE-2-RES-262K
    7. 34366
    Prev
    Next
    INDEX
    Explanations

    internal concepts and states

    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_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
    +#+#+
    0.36
     ced
    0.34
     erfolgen
    0.34
     tropomyosin
    0.34
    xE
    0.34
    је
    0.34
     এটাকে
    0.34
    ੯
    0.34
    你不
    0.34
     খাল
    0.34
    POSITIVE LOGITS
    在他的
    0.68
     lodged
    0.63
    在其
    0.61
     внутри
    0.59
    อยู่ใน
    0.59
    心中
    0.57
     ह्र
    0.54
     inside
    0.54
    在我
    0.53
    脑
    0.52
    Activations Density 0.014%

    No Known Activations