© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 2303
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns followed by family or personal items

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

    my/your purpose, question, input

    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_31_width_262k_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
    ’
    0.26
    ”。
    0.25
    ’।
    0.24
     delet
    0.23
    ين
    0.23
     $[-
    0.22
             
    0.22
     exists
    0.22
    以
    0.22
    佈
    0.22
    POSITIVE LOGITS
     favorite
    0.29
     niece
    0.29
     husband
    0.28
     wife
    0.27
    opic
    0.26
     paycheck
    0.25
    riad
    0.25
     grandmother
    0.25
    ocardial
    0.25
    opically
    0.24
    Activations Density 1.104%

    No Known Activations