© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B
    3. 40-GEMMASCOPE-2-RES-16K
    4. 11180
    Prev
    Next
    INDEX
    Explanations

    possessive pronoun + body part

    np_acts-logits-general · gemini-2.5-flash-lite

    possessive pronoun + body part

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_40_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hands
    0.70
     рук
    0.68
    hands
    0.63
     Hands
    0.62
     ног
    0.59
    🦵
    0.58
     feet
    0.57
     handen
    0.57
     manos
    0.56
     руках
    0.55
    POSITIVE LOGITS
    DR
    0.43
    Drink
    0.42
     OTHERWISE
    0.42
    乾
    0.41
    풍
    0.39
    背
    0.39
    frozen
    0.37
    Borrow
    0.37
    优秀
    0.37
     связанные
    0.37
    Activations Density 0.060%

    No Known Activations