© 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. 166514
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns followed by communication nouns

    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
    denes
    0.33
     Insert
    0.33
     Inserting
    0.32
    insert
    0.31
    ﺻ
    0.31
     tulip
    0.31
     cheeky
    0.31
    ំពោះ
    0.30
    สะอาด
    0.30
    挿
    0.30
    POSITIVE LOGITS
     commentary
    0.40
     Iod
    0.36
    评论
    0.36
     coment
    0.34
    ძ
    0.33
     Avalanche
    0.33
    コメント
    0.31
     Preface
    0.31
     empir
    0.31
     odyssey
    0.31
    Activations Density 0.000%

    No Known Activations