© 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. 7-GEMMASCOPE-2-RES-16K
    7. 14069
    Prev
    Next
    INDEX
    Explanations

    former name identification

    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_7_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
    ूक
    2.09
    ்ச
    2.08
    El
    2.08
    एप
    2.07
    ði
    2.05
    ጀ
    2.02
     Uniti
    2.01
    ӳ
    1.98
    "?>
    1.97
     फीसदी
    1.97
    POSITIVE LOGITS
    น้อง
    3.16
    นาง
    2.97
    นคร
    2.64
    นั่ง
    2.61
    יות
    2.58
    ्ता
    2.56
    mma
    2.54
    e
    2.53
    اا
    2.53
    ০
    2.51
    Activations Density 0.007%

    No Known Activations