© 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. 52041
    Prev
    Next
    INDEX
    Explanations

    addressing and calling out to people

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

    addressing audience or recipient

    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
    }{}
    0.42
    peuta
    0.41
     gotovo
    0.38
    cooked
    0.38
    mical
    0.37
    poque
    0.37
     ancak
    0.37
     &=&
    0.37
     অনেকটাই
    0.36
     confided
    0.36
    POSITIVE LOGITS
    各位同學
    0.84
     Anyone
    0.83
    各位
    0.83
     Whoever
    0.80
     PLEASE
    0.78
    Whoever
    0.78
     Please
    0.77
     ladies
    0.77
     please
    0.76
     anyone
    0.76
    Activations Density 0.095%

    No Known Activations