© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 10781
    Prev
    Next
    INDEX
    Explanations

    numbers and units

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

    numbers and units

    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
     cardiomyocyte
    0.41
     इजी
    0.41
    ٫
    0.41
    pacific
    0.40
     দশমিক
    0.39
     pacific
    0.38
    মোহ
    0.38
    gamma
    0.37
    
    0.37
    legas
    0.37
    POSITIVE LOGITS
    طي
    0.46
     Guild
    0.43
     fí
    0.42
    年生
    0.41
    పథ
    0.41
     mist
    0.41
    姆
    0.41
     Lodge
    0.40
    сыпа
    0.40
    իմ
    0.40
    Activations Density 0.215%

    No Known Activations