© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 93556
    Prev
    Next
    INDEX
    Explanations

    names starting with il or in

    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_34/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
     Перейти
    -0.92
    灭
    -0.83
     artt
    -0.82
    ENCODE
    -0.78
    udios
    -0.77
    حيث
    -0.77
    vih
    -0.77
     ComboBox
    -0.76
     כס
    -0.75
    ândia
    -0.75
    POSITIVE LOGITS
    Another
    1.04
     another
    0.99
     much
    0.95
    another
    0.93
    uddin
    0.92
     Another
    0.87
    much
    0.85
     otra
    0.81
     другой
    0.76
    Vanguard
    0.74
    Activations Density 0.085%

    No Known Activations