© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 5602
    Prev
    Next
    INDEX
    Explanations

    pronoun focus, especially questions about self

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_262k_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
     관련
    0.84
    infodisc
    0.82
     ваших
    0.80
    เหมือน
    0.79
    躹
    0.78
     noss
    0.78
     되고
    0.78
    겪
    0.77
     スウェット
    0.77
     เกี่ยว
    0.77
    POSITIVE LOGITS
     I
    1.67
    我
    1.48
     we
    1.39
     tôi
    1.22
     আমি
    1.22
    I
    1.22
     मैं
    1.19
     saya
    1.19
    আমি
    1.13
     me
    1.13
    Activations Density 0.053%

    No Known Activations