© 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. 136733
    Prev
    Next
    INDEX
    Explanations

    began appearing, wanted something

    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
    agge
    0.51
    መሳ
    0.51
    SG
    0.48
    CLAMP
    0.46
    ))=\
    0.44
    acycl
    0.44
     드릴
    0.44
    servername
    0.44
     관련된
    0.43
    LIM
    0.43
    POSITIVE LOGITS
     relieved
    0.52
     sinn
    0.49
    тинг
    0.47
    '
    0.47
    ็น
    0.47
    ্ন
    0.47
     visage
    0.46
     pochi
    0.45
     eased
    0.43
     vraag
    0.43
    Activations Density 0.003%

    No Known Activations