© 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. 117795
    Prev
    Next
    INDEX
    Explanations

    trilogies and prequels

    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
    assung
    -0.69
     activated
    -0.68
    Config
    -0.66
     služ
    -0.66
    ASSO
    -0.65
     długo
    -0.65
    tiveness
    -0.63
    Enabled
    -0.63
    机
    -0.63
     zaradi
    -0.62
    POSITIVE LOGITS
     trilogy
    4.69
     Trilogy
    3.55
    tri
    2.63
     tri
    2.58
     три
    2.30
    Tri
    2.28
    Три
    1.95
     Tri
    1.92
     triad
    1.84
     Три
    1.83
    Activations Density 0.043%

    No Known Activations