© 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. 198371
    Prev
    Next
    INDEX
    Explanations

    ideas, placement, salad, shots

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

    start of explanation

    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
     ¶
    0.49
    ы
    0.48
     piety
    0.48
     ²
    0.45
     potest
    0.45
    ¶
    0.45
     conductor
    0.43
     τε
    0.43
     ద
    0.43
    Ꮣ
    0.43
    POSITIVE LOGITS
    ینو
    0.59
     havia
    0.47
    ہنی
    0.47
     eventos
    0.45
    ോഷ്യ
    0.44
    LoginPage
    0.43
     تصاویر
    0.43
     سرکاری
    0.42
     matou
    0.42
    MaxSize
    0.42
    Activations Density 0.000%

    No Known Activations