© 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. 78897
    Prev
    Next
    INDEX
    Explanations

    IE followed by = edge or discovery

    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
     herhangi
    -0.76
    matische
    -0.75
    вання
    -0.73
     responsables
    -0.71
     lup
    -0.69
     исти
    -0.69
    ᑭ
    -0.68
     совме
    -0.68
     cose
    -0.68
    结束
    -0.68
    POSITIVE LOGITS
     IE
    0.81
     inclut
    0.73
    setContent
    0.73
    ımız
    0.73
     vantaggio
    0.72
    Torre
    0.72
     épis
    0.72
     xúc
    0.71
     trache
    0.70
     IED
    0.69
    Activations Density 0.020%

    No Known Activations