© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 19694
    Prev
    Next
    INDEX
    Explanations

    continue reading or read more

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

    mathematical representation and functions

    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
     inoxyd
    0.46
    wiches
    0.45
     limpia
    0.42
     chinois
    0.42
     lingers
    0.42
     왼
    0.41
     americanos
    0.41
    MakeRect
    0.41
    oxidase
    0.41
    Ῥ
    0.40
    POSITIVE LOGITS
     Further
    0.54
     HashMap
    0.43
    进一步
    0.42
     Andrade
    0.42
     further
    0.41
     Be
    0.41
     Signed
    0.40
     Reduced
    0.40
     Анд
    0.40
     Wrap
    0.40
    Activations Density 0.001%

    No Known Activations