© 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-16K
    7. 2825
    Prev
    Next
    INDEX
    Explanations

    banter Francis

    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_16k_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
    of
    0.46
    و
    0.43
     снижение
    0.42
    вто
    0.42
    מ
    0.41
    Erd
    0.40
    aisi
    0.39
    ุท
    0.39
    중
    0.39
    ನ್
    0.39
    POSITIVE LOGITS
     hô
    0.54
    电子邮件
    0.50
     প্রতিক
    0.49
     Léon
    0.47
     banter
    0.46
     التق
    0.45
     surfers
    0.45
     sausages
    0.44
     conferences
    0.44
     πάντα
    0.44
    Activations Density 0.040%

    No Known Activations