© 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. 64024
    Prev
    Next
    INDEX
    Explanations

    gift and blessing

    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
    尿
    -0.78
     Dienste
    -0.77
    uras
    -0.77
    vės
    -0.73
    Спасылкі
    -0.73
     brazo
    -0.72
    дела
    -0.72
    Feeding
    -0.72
    hne
    -0.71
    mapStateToProps
    -0.71
    POSITIVE LOGITS
     gift
    3.69
    gift
    3.11
     gifts
    2.70
     Gift
    2.48
    Gift
    2.45
    GIFT
    2.17
     GIFT
    2.06
    gifts
    1.84
    🎁
    1.75
     gifted
    1.74
    Activations Density 0.032%

    No Known Activations