© 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. 165821
    Prev
    Next
    INDEX
    Explanations

    catalogs and technical terms

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

    considerations for choice

    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
     verd
    0.45
    are
    0.43
     discours
    0.43
    prov
    0.43
     servis
    0.43
     gül
    0.43
    ł
    0.42
     governo
    0.42
     fün
    0.42
     wiederum
    0.42
    POSITIVE LOGITS
    0.44
    kij
    0.43
     \
    0.42
    DropDown
    0.41
     //<
    0.40
    枳
    0.40
    ↼
    0.39
    reloadData
    0.39
     Fla
    0.38
    keyDown
    0.38
    Activations Density 0.002%

    No Known Activations