© 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. 93701
    Prev
    Next
    INDEX
    Explanations

    names and specific continuations

    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
    strawberry
    -0.82
    その時
    -0.81
     خوردن
    -0.79
    働く
    -0.77
    けどね
    -0.77
     Zugang
    -0.76
    kör
    -0.75
    mushroom
    -0.75
    Sekolah
    -0.75
     children
    -0.74
    POSITIVE LOGITS
    ㎎
    0.88
     культур
    0.88
    uos
    0.81
     FAO
    0.80
    ANSAS
    0.79
     Rondo
    0.79
     cultural
    0.79
    Classifier
    0.77
    澡
    0.77
    вать
    0.77
    Activations Density 0.075%

    No Known Activations