© 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. 63979
    Prev
    Next
    INDEX
    Explanations

    Palm Triumph

    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
    أة
    -0.89
    жин
    -0.79
    untos
    -0.77
     Wul
    -0.74
    laca
    -0.74
    Dul
    -0.73
     り
    -0.73
    atak
    -0.71
    کتری
    -0.71
    AMILY
    -0.70
    POSITIVE LOGITS
     Palm
    1.23
     Triumph
    1.14
    Palm
    1.14
     waving
    1.06
    Triumph
    1.05
    triumph
    1.00
    ingresso
    0.97
     triumph
    0.96
     riding
    0.94
     Palme
    0.93
    Activations Density 0.004%

    No Known Activations