© 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. 2989
    Prev
    Next
    INDEX
    Explanations

    Muppets, Sesame Place, Scooby Doo

    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
     мной
    0.68
    <0x0D>
    0.64
    غ
    0.62
     одним
    0.62
     болезни
    0.62
    atory
    0.60
    ieder
    0.60
    </td>
    0.59
    წიფ
    0.59
     корре
    0.58
    POSITIVE LOGITS
     cartoon
    0.80
    at
    0.73
     darling
    0.73
    kon
    0.72
     lavish
    0.71
    лна
    0.71
     novi
    0.70
    দিগকে
    0.70
     has
    0.70
     policeman
    0.69
    Activations Density 0.003%

    No Known Activations