© 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. 77423
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns and room types

    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
    vikle
    -0.79
    ⟬
    -0.75
    äts
    -0.71
    たちに
    -0.70
    西装
    -0.70
    խ
    -0.70
    @
    -0.70
    (@"%@",
    -0.69
     sidewalks
    -0.69
    ANKS
    -0.69
    POSITIVE LOGITS
     room
    4.47
     rooms
    3.55
     bedroom
    3.42
     Room
    2.84
    Room
    2.78
    room
    2.77
    房间
    2.75
     ROOM
    2.69
     bedrooms
    2.64
    部屋
    2.61
    Activations Density 0.025%

    No Known Activations