© 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. 40-GEMMASCOPE-2-RES-262K
    7. 210353
    Prev
    Next
    INDEX
    Explanations

    temperature in degrees Fahrenheit

    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_40_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
     FT
    0.43
    ſt
    0.41
    FT
    0.37
     เมือง
    0.37
    洍
    0.37
    atering
    0.36
    ുമ്പോൾ
    0.36
    Ft
    0.36
     Bort
    0.36
     townships
    0.36
    POSITIVE LOGITS
     ActionBar
    0.41
    ंकित
    0.41
    ज्ञ
    0.40
     அகத்திய
    0.39
     Classic
    0.39
     카
    0.39
     쓰
    0.39
     Container
    0.38
     jelly
    0.38
     Nietzsche
    0.38
    Activations Density 0.002%

    No Known Activations