© 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. 78528
    Prev
    Next
    INDEX
    Explanations

    available or up for sale

    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
    irin
    -0.85
    asel
    -0.80
    yam
    -0.77
    ว์
    -0.76
    anko
    -0.75
     Beschäf
    -0.75
    implemented
    -0.75
     zare
    -0.74
     beſ
    -0.72
    帙
    -0.72
    POSITIVE LOGITS
     up
    4.34
    Up
    2.06
     Up
    1.91
     available
    1.87
    up
    1.71
    ขึ้น
    1.43
     lên
    1.37
     UP
    1.28
    アップ
    1.25
     open
    1.24
    Activations Density 0.045%

    No Known Activations