© 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. 93527
    Prev
    Next
    INDEX
    Explanations

    inspiration and inspiring

    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
    ാം
    -0.87
     inkluder
    -0.84
     ++)
    -0.83
    bentuk
    -0.82
    👅
    -0.81
    ངས་
    -0.79
    ulu
    -0.79
    .../
    -0.79
    ップ
    -0.76
    shtml
    -0.76
    POSITIVE LOGITS
     inspiration
    6.97
     Inspiration
    5.28
     inspire
    5.19
    inspiration
    5.13
    Inspiration
    5.00
     inspired
    5.00
     inspirations
    4.91
     inspires
    4.78
     inspira
    4.47
     inspir
    4.44
    Activations Density 0.124%

    No Known Activations