© 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. 31597
    Prev
    Next
    INDEX
    Explanations

    he or she/her

    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
     her
    -3.27
    她的
    -2.41
     ее
    -2.41
     її
    -2.39
     её
    -2.17
     její
    -2.16
     ihren
    -1.96
     ihrem
    -1.91
     ihrer
    -1.88
     jej
    -1.87
    POSITIVE LOGITS
     his
    2.45
     she
    2.42
     jego
    1.88
     она
    1.86
     его
    1.79
     njego
    1.71
    she
    1.66
     його
    1.59
    his
    1.59
     seiner
    1.53
    Activations Density 0.030%

    No Known Activations