© 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. 4742
    Prev
    Next
    INDEX
    Explanations

    winning, momentum, attacking, intensity

    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
    とい
    0.40
    ్ఞ
    0.39
    
    0.39
    Raleway
    0.38
    ិត
    0.38
    Karte
    0.38
    Từ
    0.38
     ರಿಂದ
    0.38
    農
    0.38
    மர
    0.38
    POSITIVE LOGITS
     momentum
    0.50
     confidence
    0.47
     धमाकेदार
    0.47
     thrives
    0.46
     resurgence
    0.46
     revamped
    0.45
     performance
    0.45
     rallies
    0.45
     blistering
    0.45
     debuting
    0.44
    Activations Density 0.042%

    No Known Activations