© 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-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 76408
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns followed by family members

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_width_262k_l0_small_affine
    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
     LSR
    0.31
     لدى
    0.30
     Observ
    0.27
    ǫ
    0.27
     enjoying
    0.27
     dedic
    0.27
     LAR
    0.27
     attending
    0.27
     attendance
    0.27
    дол
    0.27
    POSITIVE LOGITS
    ACTER
    0.31
     задачу
    0.31
    窍
    0.30
    ឿ
    0.29
    че
    0.29
    espère
    0.29
    ួត
    0.29
    ന്യൂ
    0.28
     объ
    0.28
     обу
    0.27
    Activations Density 0.003%

    No Known Activations