© 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. 148986
    Prev
    Next
    INDEX
    Explanations

    words following named entities

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

    influences and check pediatric data

    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
    MemberList
    0.49
     直
    0.48
     agrupación
    0.48
     তাঁরা
    0.46
     partnering
    0.45
     Д
    0.43
     собственности
    0.43
     компания
    0.42
     команд
    0.42
     ቡ
    0.42
    POSITIVE LOGITS
    zd
    0.54
    zad
    0.50
    gerald
    0.49
    rm
    0.49
    wod
    0.48
    rit
    0.48
    ha
    0.48
    ung
    0.47
    te
    0.47
    ge
    0.47
    Activations Density 0.001%

    No Known Activations