© 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. 31-GEMMASCOPE-2-RES-262K
    7. 52682
    Prev
    Next
    INDEX
    Explanations

    transparency and quantity

    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_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
    ಲಾಗಿದೆ
    0.39
    надца
    0.38
     malicious
    0.38
     welchen
    0.38
    贼
    0.38
     但是
    0.37
     sniper
    0.37
    ንሽ
    0.37
    icted
    0.37
     olisi
    0.36
    POSITIVE LOGITS
    ی
    0.51
    性和
    0.48
    மார்
    0.46
     Vou
    0.44
    *",
    0.44
    estructura
    0.44
     উভয়ের
    0.43
    ユニット
    0.43
     修
    0.43
    s
    0.41
    Activations Density 0.014%

    No Known Activations