© 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. 58325
    Prev
    Next
    INDEX
    Explanations

    unsafe casting and imports

    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
    hatian
    -0.79
    exemplar
    -0.77
     Though
    -0.73
    رنگ
    -0.72
    Rough
    -0.72
    之下
    -0.72
     Just
    -0.72
     menengah
    -0.71
     lapisan
    -0.71
    cú
    -0.71
    POSITIVE LOGITS
     reinterpret
    1.07
    cast
    0.93
    reinterpret
    0.88
     cast
    0.84
    JECTION
    0.82
     vielmehr
    0.81
     saudável
    0.80
    吃完
    0.80
    archar
    0.78
    uais
    0.77
    Activations Density 0.002%

    No Known Activations