© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 93258
    Prev
    Next
    INDEX
    Explanations

    type casting and dynamic allocation

    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
    lector
    -0.81
    Ja
    -0.79
    Ἥ
    -0.77
     Flame
    -0.77
     Iron
    -0.77
     then
    -0.76
     iron
    -0.76
     Fla
    -0.75
    rav
    -0.74
     Pharma
    -0.74
    POSITIVE LOGITS
     dynamic
    1.91
     static
    1.72
    dynamic
    1.64
    static
    1.45
    reinterpret
    1.27
     DYNAMIC
    1.23
     dynamique
    1.23
     reinterpret
    1.16
     динами
    1.15
    动态
    1.08
    Activations Density 0.009%

    No Known Activations