© 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
    2. Gemma-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 137834
    Prev
    Next
    INDEX
    Explanations

    chartered and certified classifications

    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
    ských
    0.65
    奋斗
    0.64
    smittel
    0.63
    지
    0.62
    schule
    0.61
    πτωση
    0.60
    science
    0.60
    ต์
    0.60
    hilfe
    0.59
    くなる
    0.59
    POSITIVE LOGITS
     powied
    0.75
     to
    0.73
    س
    0.68
    Vous
    0.68
    routes
    0.65
    Were
    0.65
     Chartered
    0.65
    )”.
    0.64
     routes
    0.64
     inl
    0.64
    Activations Density 0.000%

    No Known Activations