© 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. 7115
    Prev
    Next
    INDEX
    Explanations

    and followed by a, open, coming, how, balanced, what

    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
    ↵
    0.29
     investigates
    0.28
     includes
    0.27
     للح
    0.27
     guides
    0.26
    ウェ
    0.25
     accessories
    0.25
     studies
    0.25
     ਵ
    0.25
     include
    0.24
    POSITIVE LOGITS
    ONENT
    0.28
     bemo
    0.26
     చేసి
    0.26
     siis
    0.26
     lihtsalt
    0.26
     പിന്നെ
    0.25
     그걸
    0.25
     irgendwie
    0.25
    स्पेक्ट
    0.25
     желания
    0.25
    Activations Density 0.198%

    No Known Activations