© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 13646
    Prev
    Next
    INDEX
    Explanations

    preferred pronouns and preferences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    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
    n
    0.84
    א
    0.83
    ط
    0.79
    ท
    0.78
    ก
    0.77
    ב
    0.77
    ה
    0.75
    _
    0.75
    ห
    0.75
    т
    0.73
    POSITIVE LOGITS
     preferences
    1.04
     préférences
    1.04
     preference
    1.01
     preferências
    0.91
     Preference
    0.89
    preference
    0.86
     preferencia
    0.84
     предпоч
    0.82
     Preferences
    0.81
     prefer
    0.79
    Activations Density 0.104%

    No Known Activations