© 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-3-1B
    5. 17-GEMMASCOPE-2-RES-16K
    7. 2130
    Prev
    Next
    INDEX
    Explanations

    Okay, let's break down

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_17_width_16k_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
     tôi
    1.71
    私は
    1.64
    俺
    1.60
     کردم
    1.57
    我不
    1.54
     ನನಗೆ
    1.53
     vuttam
    1.52
     मला
    1.52
    譏
    1.51
    avaient
    1.51
    POSITIVE LOGITS
     your
    2.84
    your
    2.46
     Your
    2.17
     yourself
    2.16
    Your
    2.09
     আপনার
    2.07
     YOUR
    2.04
     vaš
    2.04
     உங்கள்
    2.02
     તમારા
    1.99
    Activations Density 0.894%

    No Known Activations