© 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. 16-GEMMASCOPE-2-RES-262K
    7. 18297
    Prev
    Next
    INDEX
    Explanations

    what is enjoyed

    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_16_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
     is
    0.81
     oysters
    0.71
     Бі
    0.70
     Ҳ
    0.70
     た
    0.69
     Бе
    0.68
     insulator
    0.68
     Jeśli
    0.67
     beetles
    0.67
     Фа
    0.66
    POSITIVE LOGITS
    u
    0.98
    r
    0.88
    ,
    0.86
    b
    0.80
    i
    0.79
    9
    0.78
    <0x80>
    0.77
    the
    0.77
    and
    0.76
    at
    0.71
    Activations Density 0.005%

    No Known Activations