© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 999
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns followed by body parts

    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
    ში
    -0.77
    istungs
    -0.72
    歙
    -0.71
    𝙶
    -0.69
    ocate
    -0.69
    ikum
    -0.69
    кли
    -0.69
     Quincy
    -0.68
    だという
    -0.68
    議会
    -0.67
    POSITIVE LOGITS
     hand
    4.56
     hands
    2.88
    hand
    2.84
     руку
    2.83
    Hand
    2.73
     arm
    2.59
     fingers
    2.53
     Hand
    2.50
     finger
    2.38
    手
    2.27
    Activations Density 0.059%

    No Known Activations