© 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. 38430
    Prev
    Next
    INDEX
    Explanations

    informal male address

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

    informal terms of address

    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
     Ông
    0.55
    Ông
    0.54
    ת
    0.53
    እና
    0.52
    射
    0.49
    Пер
    0.49
    항
    0.49
    秘书
    0.48
    代表人
    0.48
    🫣
    0.48
    POSITIVE LOGITS
     dude
    0.51
     rus
    0.47
     raj
    0.46
     grassroots
    0.46
     rain
    0.45
     fuelwood
    0.43
    illance
    0.43
     unfolded
    0.43
     dedic
    0.42
     girl
    0.42
    Activations Density 0.009%

    No Known Activations