© 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. 34-GEMMASCOPE-RES-131K
    4. 80895
    Prev
    Next
    INDEX
    Explanations

    Computer science and lab terms

    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
    warten
    -0.80
    dann
    -0.79
    spes
    -0.77
    tragen
    -0.77
    izowane
    -0.74
     toallas
    -0.72
    kontrolle
    -0.70
     Trumb
    -0.70
    Svara
    -0.69
    嫱
    -0.69
    POSITIVE LOGITS
     연구
    0.77
    īts
    0.76
     femoral
    0.75
     getResource
    0.75
    luiting
    0.73
    lieb
    0.73
     Glaubens
    0.71
    heran
    0.71
     tasteless
    0.71
    yendo
    0.70
    Activations Density 0.001%

    No Known Activations