© 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. 51143
    Prev
    Next
    INDEX
    Explanations

    who goes

    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
     commended
    0.53
    Описание
    0.50
    Хар
    0.47
    П
    0.47
    Й
    0.46
    Бу
    0.46
    Согласно
    0.45
    Ста
    0.44
    夏の
    0.43
    ג
    0.43
    POSITIVE LOGITS
    art
    0.52
    ajoz
    0.49
    dell
    0.44
    umbre
    0.43
    transformers
    0.43
    umb
    0.42
     ont
    0.42
    ki
    0.41
    rat
    0.41
     alles
    0.41
    Activations Density 0.003%

    No Known Activations