© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 50292
    Prev
    Next
    INDEX
    Explanations

    pattern of issues or existence

    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
     bhfu
    0.48
     lousy
    0.46
     mommy
    0.45
     creepy
    0.44
    uração
    0.44
     reclaimed
    0.44
    }[(
    0.43
     treasures
    0.43
     de
    0.42
     obtained
    0.42
    POSITIVE LOGITS
    зить
    0.46
    GIS
    0.45
    ंद
    0.42
    著
    0.42
    Our
    0.41
    CI
    0.40
    ૧
    0.40
    Archives
    0.40
    льбе
    0.40
    Premi
    0.39
    Activations Density 0.013%

    No Known Activations