© 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. 22765
    Prev
    Next
    INDEX
    Explanations

    nature documentary, lost or; dropdown wrapper

    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
     Nee
    0.50
    agées
    0.48
    菽
    0.47
     isAdmin
    0.46
     лиш
    0.44
     Бала
    0.44
     sétimo
    0.43
     дума
    0.43
     diamètre
    0.42
    辣椒
    0.42
    POSITIVE LOGITS
     (
    0.42
    tests
    0.37
    gloss
    0.37
    ($"
    0.37
    ⁡</
    0.36
    ERT
    0.36
     Botswana
    0.36
     விரும்ப
    0.36
    positroid
    0.36
    cnt
    0.35
    Activations Density 0.001%

    No Known Activations