© 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. 80927
    Prev
    Next
    INDEX
    Explanations

    static_cast

    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
     everything
    -0.80
    他們的
    -0.75
    绯
    -0.74
    そのため
    -0.72
    ären
    -0.72
    主婦
    -0.72
     手工
    -0.71
    nium
    -0.71
    があり
    -0.71
    reebok
    -0.70
    POSITIVE LOGITS
    CAST
    1.58
    cast
    1.58
     cast
    1.53
     CAST
    1.45
     Cast
    1.44
    Cast
    1.41
     casts
    1.32
    casts
    1.16
     casting
    1.09
     castings
    1.09
    Activations Density 0.005%

    No Known Activations