© 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-65K
    7. 49575
    Prev
    Next
    INDEX
    Explanations

    calculations and data

    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_65k_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
     Publication
    0.43
     latter
    0.41
    .`);
    0.41
     Rho
    0.41
     எளி
    0.40
     Artist
    0.40
     Constraints
    0.40
    后者
    0.40
     Management
    0.39
    .</
    0.39
    POSITIVE LOGITS
    🚨
    0.47
    ახებ
    0.44
    比起
    0.43
     indicator
    0.43
    MILL
    0.42
     çocuklar
    0.42
     insurers
    0.42
     headsets
    0.42
    ۪
    0.42
    services
    0.40
    Activations Density 0.003%

    No Known Activations