© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 2539
    Prev
    Next
    INDEX
    Explanations

    possessives and ownership

    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_40_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
     the
    0.31
     an
    0.30
     a
    0.30
     positioned
    0.27
     be
    0.27
     in
    0.26
     each
    0.25
     certain
    0.25
     iteratively
    0.25
    -
    0.25
    POSITIVE LOGITS
     own
    0.57
     eigenes
    0.38
     Own
    0.38
     próprias
    0.38
     eigenen
    0.37
     propios
    0.37
     propias
    0.36
     собственные
    0.36
     OWN
    0.35
     próprio
    0.34
    Activations Density 0.410%

    No Known Activations