© 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. 96566
    Prev
    Next
    INDEX
    Explanations

    number of nights

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

    nights and days

    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
    幢
    0.45
    MIC
    0.44
    ссий
    0.43
     талант
    0.42
    bss
    0.41
    Ainsi
    0.41
     MBP
    0.41
    MB
    0.40
     เงี้ย
    0.40
    ينات
    0.40
    POSITIVE LOGITS
     আপাতত
    0.49
     ተጨማሪ
    0.48
     ਨ
    0.48
     pim
    0.47
     looming
    0.47
    讨厌
    0.46
     pago
    0.46
     Stop
    0.46
     pind
    0.45
    เพิ่มเติม
    0.45
    Activations Density 0.000%

    No Known Activations