© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 111762
    Prev
    Next
    INDEX
    Explanations

    help to achieve or understand

    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_10/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
    蹩
    -1.55
     регионе
    -1.51
     możliwość
    -1.48
    erweise
    -1.44
     it
    -1.42
     erklärte
    -1.40
    哈哈哈
    -1.39
     voisins
    -1.36
     tradicionales
    -1.35
     اما
    -1.32
    POSITIVE LOGITS
    <
    1.55
     الوزراء
    1.51
    .
    1.48
     não
    1.46
    S
    1.45
    taglio
    1.44
    ichtete
    1.43
    begin
    1.42
    🩻
    1.39
     nakalista
    1.38
    Activations Density 0.010%

    No Known Activations