Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8653
    Prev
    Next
    INDEX
    Explanations

    Texas and Texarkana

    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
     from
    -2.61
     with
    -2.52
     in
    -2.45
     for
    -2.38
     only
    -2.34
     by
    -2.33
     first
    -2.27
     through
    -2.22
     one
    -2.22
     on
    -2.14
    POSITIVE LOGITS
    mainly
    2.06
    primarily
    2.06
    ఽ
    2.02
    didn
    1.96
    actually
    1.93
    belie
    1.93
    generally
    1.93
    commonly
    1.93
    probably
    1.87
     gigantic
    1.87
    Activations Density 0.021%

    No Known Activations