© 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. 40-GEMMASCOPE-2-RES-16K
    7. 10000
    Prev
    Next
    INDEX
    Explanations

    version numbers

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

    installing python packages with pip

    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_40_width_16k_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
    obe
    0.43
     decimos
    0.41
     RS
    0.40
    2
    0.40
    inal
    0.40
    ultima
    0.40
    ac
    0.39
    RS
    0.39
    patched
    0.39
     (
    0.39
    POSITIVE LOGITS
     આરો
    0.42
    Ϻ
    0.41
    蘼
    0.39
     आम
    0.39
    路線
    0.39
     جات
    0.38
    スティ
    0.38
     handleError
    0.38
     금액
    0.38
     قوس
    0.38
    Activations Density 0.003%

    No Known Activations