© 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-65K
    7. 30314
    Prev
    Next
    INDEX
    Explanations

    Enterprise Special Zone

    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_65k_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
    ር
    0.45
    fixtures
    0.43
    ર
    0.41
    س
    0.39
    ර්
    0.38
    جو
    0.38
    ष
    0.38
    impurity
    0.38
    ༸
    0.38
    provides
    0.38
    POSITIVE LOGITS
     Mai
    0.53
     Potato
    0.51
     ratified
    0.51
     Government
    0.49
    стрі
    0.49
     neuer
    0.49
     Neither
    0.48
     но
    0.47
     Governo
    0.47
     用户
    0.47
    Activations Density 0.003%

    No Known Activations