© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 141040
    Prev
    Next
    INDEX
    Explanations

    shy away from

    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_16_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
    平和
    0.49
     પોતા
    0.45
    亚太
    0.43
     enviable
    0.39
     стану
    0.39
     рабо
    0.39
    ’.
    0.39
    </
    0.38
     parlare
    0.38
     rekord
    0.38
    POSITIVE LOGITS
    enix
    0.59
    hydroxyl
    0.56
     baar
    0.54
    heater
    0.50
    oxyd
    0.50
    ＮＡＮＡ
    0.49
     टिश
    0.49
    convex
    0.48
     மஞ்சள்
    0.48
    CIF
    0.48
    Activations Density 0.001%

    No Known Activations