© 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. 86968
    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
    éndole
    -0.92
    něte
    -0.84
    ᅱ
    -0.78
    anap
    -0.78
     گذاشت
    -0.77
     rejoindre
    -0.77
     Celine
    -0.75
     nowego
    -0.75
     potwier
    -0.74
    cky
    -0.73
    POSITIVE LOGITS
     static
    3.08
    static
    2.89
    静态
    1.58
     Static
    1.48
    Static
    1.46
    静
    1.30
     std
    1.20
    STATIC
    1.16
     stationary
    1.11
    std
    1.10
    Activations Density 0.010%

    No Known Activations