© 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-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 19839
    Prev
    Next
    INDEX
    Explanations

    speaker pronouns and possessives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ducible
    0.46
     bewildered
    0.43
    あるいは
    0.41
    Regulatory
    0.40
    睨
    0.40
    expression
    0.40
    aric
    0.39
    বাদের
    0.39
     elaboration
    0.38
    భ
    0.38
    POSITIVE LOGITS
     minha
    0.77
     moje
    0.76
     наши
    0.73
     our
    0.73
     мои
    0.72
     моих
    0.72
     nossos
    0.70
     minhas
    0.69
     we
    0.68
     nossa
    0.68
    Activations Density 0.024%

    No Known Activations