© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 84620
    Prev
    Next
    INDEX
    Explanations

    make it easier

    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
    lierung
    -0.95
     cannot
    -0.90
    ('<
    -0.84
    rosi
    -0.83
    ulam
    -0.81
    lores
    -0.80
     made
    -0.79
     издание
    -0.79
    {_
    -0.78
    しかし
    -0.77
    POSITIVE LOGITS
     available
    2.44
    Available
    1.60
    available
    1.42
     it
    1.34
     Available
    1.31
     AVAILABLE
    1.23
     sure
    1.23
     disponibles
    1.21
     доступ
    1.20
    AVAILABLE
    1.16
    Activations Density 0.038%

    No Known Activations