© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 200686
    Prev
    Next
    INDEX
    Explanations

    concepts, categories, and specific items

    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
     اتمنى
    0.44
    ジャケット
    0.43
     sabemos
    0.42
     cartera
    0.41
    0.41
    cket
    0.40
    胳
    0.40
     togetherness
    0.40
     pelea
    0.40
    😩
    0.40
    POSITIVE LOGITS
     σημα
    0.48
     শিষ
    0.46
     Conce
    0.43
     Modes
    0.41
     чет
    0.41
     стоимо
    0.41
     மறை
    0.40
    이었다
    0.40
     Marvel
    0.39
     способов
    0.39
    Activations Density 0.004%

    No Known Activations