© 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. 21166
    Prev
    Next
    INDEX
    Explanations

    specific domains, tasks, and content

    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
     kadang
    0.47
     solcher
    0.43
     themselves
    0.42
    _{-}
    0.41
     guests
    0.41
     bystanders
    0.40
     enfants
    0.40
    SaveChanges
    0.40
     audiences
    0.40
    clientWidth
    0.38
    POSITIVE LOGITS
     particulier
    0.51
     має
    0.49
     particulière
    0.48
    ത്രം
    0.45
    Particular
    0.43
    ならでは
    0.42
     particuliers
    0.41
    愁
    0.41
    дження
    0.41
     وہی
    0.41
    Activations Density 0.055%

    No Known Activations