© 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. 44169
    Prev
    Next
    INDEX
    Explanations

    art style specifics or programming loops

    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
    baw
    0.45
     militar
    0.44
     mercantile
    0.43
    ි
    0.43
     misfort
    0.42
     절대
    0.42
     liqu
    0.42
     voto
    0.42
    “-
    0.42
    andfeel
    0.42
    POSITIVE LOGITS
     for
    0.45
     บท
    0.44
     For
    0.44
     epitope
    0.43
     Elementary
    0.43
     неожидан
    0.43
     Asalamualaikum
    0.42
     गया
    0.41
     обнару
    0.41
    वरून
    0.40
    Activations Density 0.005%

    No Known Activations