© 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. 126842
    Prev
    Next
    INDEX
    Explanations

    test of time

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

    considerations and sensitive topics

    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
     faster
    0.45
    ফ
    0.45
     things
    0.45
     anchorage
    0.45
     języ
    0.44
     Ile
    0.44
     chute
    0.44
     Chu
    0.43
     мяг
    0.43
     Anglia
    0.43
    POSITIVE LOGITS
    危害
    0.50
     彼
    0.47
    素质
    0.47
    詆
    0.45
     及び
    0.45
    npj
    0.45
    及び
    0.44
    他們的
    0.44
    詡
    0.43
    他们的
    0.42
    Activations Density 0.000%

    No Known Activations