© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 79577
    Prev
    Next
    INDEX
    Explanations

    numbers, symbols, file paths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lllll
    -1.17
     querem
    -1.14
    asties
    -1.10
    perity
    -1.10
     Fähigkeiten
    -1.09
    warden
    -1.05
    䛗
    -1.05
    uminum
    -1.04
    metres
    -1.03
    plevel
    -1.03
    POSITIVE LOGITS
    ときの
    1.12
    様な
    1.06
     S
    1.02
    M
    1.02
     Эти
    0.99
     discernible
    0.98
     M
    0.95
    eara
    0.92
    ッセージ
    0.92
     Appellants
    0.91
    Activations Density 0.001%

    No Known Activations