© 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. 79411
    Prev
    Next
    INDEX
    Explanations

    not in

    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
     árboles
    0.44
     används
    0.44
    ٍ
    0.43
    ﮑ
    0.43
    JobID
    0.42
    划
    0.41
     ö
    0.40
    ismarck
    0.39
    狙
    0.39
    흩
    0.39
    POSITIVE LOGITS
     corrects
    0.48
     panier
    0.45
    ্ধে
    0.45
    DAN
    0.44
     루
    0.43
    담
    0.43
     retr
    0.43
     toug
    0.43
    oja
    0.43
     이야
    0.42
    Activations Density 0.001%

    No Known Activations