© 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-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 1633
    Prev
    Next
    INDEX
    Explanations

    physical specific widely experiential

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_17_width_16k_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
     Niem
    0.67
    يانة
    0.64
     ছাড়াই
    0.63
     lymphoma
    0.61
    的情况
    0.61
    etragen
    0.61
    的情況
    0.60
    繧
    0.59
     গবে
    0.59
     Lucky
    0.59
    POSITIVE LOGITS
     physical
    2.03
     physically
    1.86
    Physical
    1.83
     Physical
    1.79
     tangible
    1.77
    physical
    1.72
     physicality
    1.60
     fysis
    1.56
     PHYSICAL
    1.56
     practical
    1.56
    Activations Density 3.082%

    No Known Activations