© 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. 7879
    Prev
    Next
    INDEX
    Explanations

    Chance, seeing, working, April

    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
     різ
    0.37
    Configuration
    0.37
    Editing
    0.35
     distant
    0.35
    ંગ
    0.35
     verso
    0.34
    Robust
    0.34
    向
    0.34
    Against
    0.34
    udet
    0.34
    POSITIVE LOGITS
    ギラ
    0.44
     ्
    0.42
     سلسله
    0.39
     miejscowości
    0.39
     niew
    0.39
     calculer
    0.39
     Aluminum
    0.38
    葚
    0.37
     hidro
    0.36
    棫
    0.36
    Activations Density 0.002%

    No Known Activations