© 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. 8293
    Prev
    Next
    INDEX
    Explanations

    information retrieval and details

    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
    畀
    0.40
    しばらく
    0.40
    乐队
    0.40
    绁
    0.39
    とりあえず
    0.39
    啝
    0.39
     परियोजनाओं
    0.39
     полити
    0.38
    掮
    0.38
    Bookmark
    0.38
    POSITIVE LOGITS
     furthermore
    0.45
     detailed
    0.43
     correctly
    0.43
     clinically
    0.42
     qualities
    0.41
     additionally
    0.41
     retrieval
    0.41
     R
    0.40
     details
    0.40
     characteristics
    0.40
    Activations Density 0.004%

    No Known Activations