© 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. 117762
    Prev
    Next
    INDEX
    Explanations

    pampering, spoiled kids

    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
    jegy
    -0.84
    utory
    -0.72
    ary
    -0.71
     duyên
    -0.69
    eschou
    -0.68
    ACITY
    -0.68
     belegt
    -0.68
     umane
    -0.66
     Sl
    -0.66
    Eksteraj
    -0.66
    POSITIVE LOGITS
     pam
    3.39
     cod
    2.81
    pam
    2.36
     molly
    2.17
    Pam
    1.93
     spoon
    1.77
     Pam
    1.64
     bab
    1.64
    Cod
    1.62
     Cod
    1.60
    Activations Density 0.035%

    No Known Activations