© 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. 31-GEMMASCOPE-2-RES-16K
    4. 3465
    Prev
    Next
    INDEX
    Explanations

    versions and proposed advantages

    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
    <unused562>
    0.49
    <unused367>
    0.47
    <unused1718>
    0.45
     い
    0.44
    ﺣ
    0.43
     vehemently
    0.43
    <unused502>
    0.42
     го
    0.42
    ье
    0.42
    <unused274>
    0.41
    POSITIVE LOGITS
    版的
    0.57
    版本的
    0.49
    ation
    0.46
     versions
    0.44
    版
    0.44
     
    0.43
    ized
    0.41
     version
    0.41
    ification
    0.40
    omeric
    0.39
    Activations Density 0.369%

    No Known Activations