© 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-262K
    7. 13779
    Prev
    Next
    INDEX
    Explanations

    uncertainty or possibility

    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_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
     மூன்று
    0.38
     جميع
    0.38
     ہے۔
    0.38
     ڈی
    0.34
    ⒈
    0.34
    ۔
    0.32
     நான்கு
    0.32
    ْ
    0.32
     네
    0.31
     interrelated
    0.31
    POSITIVE LOGITS
     magari
    0.47
     perhaps
    0.41
     vielleicht
    0.40
     হয়তো
    0.39
     شاید
    0.39
     maybe
    0.39
     nějak
    0.37
     seem
    0.37
     possa
    0.37
    确实
    0.36
    Activations Density 0.019%

    No Known Activations