© 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. 31-GEMMASCOPE-2-RES-65K
    7. 48729
    Prev
    Next
    INDEX
    Explanations

    foreign words and diverse topics

    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_31_width_65k_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
     stara
    0.44
     моде
    0.43
     עי
    0.43
    GUILayout
    0.43
    껌
    0.42
     разом
    0.42
     לפי
    0.42
     ಶ
    0.42
     רי
    0.41
     rosem
    0.41
    POSITIVE LOGITS
    ची
    0.50
     virkelig
    0.50
    azing
    0.47
     később
    0.46
    让我们
    0.46
    决定
    0.46
    成为
    0.45
    也是
    0.43
    泄漏
    0.43
    丽
    0.43
    Activations Density 0.007%

    No Known Activations