© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 6984
    Prev
    Next
    INDEX
    Explanations

    0

    np_acts-logits-general · gemini-2.5-flash-lite

    statues and their prohibitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     trám
    0.41
    ୫
    0.40
     لگاتا
    0.39
     couv
    0.39
     tý
    0.38
     來
    0.38
     uniques
    0.38
     فایل
    0.37
     wykony
    0.37
    Methylsulfanyl
    0.37
    POSITIVE LOGITS
     harmful
    0.36
    itution
    0.36
    &
    0.36
     advantageous
    0.36
    3
    0.36
     whe
    0.35
    l
    0.35
     injurious
    0.35
    б
    0.35
     emerged
    0.35
    Activations Density 0.084%

    No Known Activations