© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49601
    Prev
    Next
    INDEX
    Explanations

    invalid or exception

    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
    {~
    -0.85
    Significant
    -0.78
     jelent
    -0.75
     ski
    -0.73
     jangka
    -0.70
     speaking
    -0.70
     prosedur
    -0.70
     stoves
    -0.69
    𝗔
    -0.68
     są
    -0.68
    POSITIVE LOGITS
    不管是
    0.83
     đầm
    0.80
    PLN
    0.75
    RenderTarget
    0.73
     coloris
    0.73
    ového
    0.72
    声明
    0.72
     exposé
    0.71
     edili
    0.71
     continuant
    0.71
    Activations Density 0.007%

    No Known Activations