© 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. 108455
    Prev
    Next
    INDEX
    Explanations

    intent or intention

    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
    寕
    -1.07
    ⽅
    -1.05
     differing
    -1.04
     enraged
    -1.03
     conclusive
    -1.02
    フォト
    -1.02
     resounding
    -1.01
    雱
    -1.01
     снег
    -1.00
     Geschä
    -0.97
    POSITIVE LOGITS
     to
    1.20
    ции
    1.01
    IONS
    0.95
    Gear
    0.92
    赅
    0.91
     audience
    0.91
     purposes
    0.91
    Garonne
    0.90
     ,\
    0.90
    ),
    0.89
    Activations Density 0.015%

    No Known Activations