© 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. 204007
    Prev
    Next
    INDEX
    Explanations

    outer

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

    numbers and lists

    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
    ˆ‚
    0.59
     Toxicol
    0.47
     Ereign
    0.45
     Dern
    0.43
     冷
    0.43
    ทด
    0.43
     Andrés
    0.42
     Scandal
    0.42
     Schultz
    0.42
     Él
    0.42
    POSITIVE LOGITS
     number
    0.49
    Number
    0.47
     let
    0.46
     everywhere
    0.45
     double
    0.44
    چھا
    0.43
    每周
    0.42
     менее
    0.42
     numbers
    0.42
    ﺿ
    0.42
    Activations Density 0.002%

    No Known Activations