© 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. 36697
    Prev
    Next
    INDEX
    Explanations

    flirt, compliments, arguments, strategies

    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
    은
    0.47
     극
    0.46
    Storyboard
    0.44
     দীপ
    0.43
    ")
    0.43
     예
    0.43
    这
    0.43
    自己
    0.43
     덕
    0.42
    រូប
    0.41
    POSITIVE LOGITS
     suficientes
    0.55
     aient
    0.46
    went
    0.45
     hating
    0.45
    থেষ্ট
    0.45
     específicos
    0.44
    テイ
    0.44
     adecuados
    0.43
     persuas
    0.43
     lemah
    0.42
    Activations Density 0.021%

    No Known Activations