© 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. 32081
    Prev
    Next
    INDEX
    Explanations

    quoted speech attribution

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

    quoted speech followed by a determiner

    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
     spoke
    0.54
     singer
    0.54
    ز
    0.54
     four
    0.53
     yeah
    0.52
     tourism
    0.51
     gruesome
    0.51
     fryer
    0.50
    chens
    0.50
     nine
    0.50
    POSITIVE LOGITS
    。
    0.52
    an
    0.50
    )。
    0.49
    从而
    0.47
    嶈
    0.46
    ど
    0.46
    ).
    0.45
    相比
    0.44
    RL
    0.44
    anlı
    0.43
    Activations Density 0.011%

    No Known Activations