© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 11560
    Prev
    Next
    INDEX
    Explanations

    occurrence or state change

    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
    私
    0.43
     reflexion
    0.43
    icur
    0.41
    কেন্ড
    0.41
    edics
    0.40
     охла
    0.40
    慎
    0.40
    Ճ
    0.39
     nacionales
    0.39
     doable
    0.39
    POSITIVE LOGITS
    .,
    0.48
     Auckland
    0.47
    $.;
    0.47
     Constitu
    0.46
     cambiamenti
    0.45
     ต้องการ
    0.44
     numérique
    0.44
    AAP
    0.44
     Category
    0.43
    .),
    0.43
    Activations Density 0.000%

    No Known Activations