© 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. 119521
    Prev
    Next
    INDEX
    Explanations

    founded or established year

    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
    始まる
    0.44
    ﺐ
    0.43
    吒
    0.43
     Wikipedia
    0.41
    始まった
    0.41
     約
    0.39
     zahval
    0.39
     póź
    0.39
     وزير
    0.39
     सुरुवात
    0.38
    POSITIVE LOGITS
     established
    0.42
     Established
    0.41
    Established
    0.40
     januar
    0.38
    ेश्व
    0.37
     brokerage
    0.37
     dương
    0.37
     since
    0.37
     wang
    0.37
    𝟭
    0.37
    Activations Density 0.002%

    No Known Activations