© 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. 40-GEMMASCOPE-2-RES-262K
    7. 166501
    Prev
    Next
    INDEX
    Explanations

    specific words and punctuation

    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_40_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
    韓國
    0.54
    崗
    0.49
    ياز
    0.48
    搠
    0.46
    🇰
    0.46
     韓国
    0.45
     Hàn
    0.45
    និយ
    0.45
    跚
    0.45
    Jdbc
    0.45
    POSITIVE LOGITS
     py
    0.46
     x
    0.44
     må
    0.43
     coast
    0.42
    proc
    0.42
    ad
    0.42
     her
    0.42
     de
    0.42
     proc
    0.42
    Ella
    0.42
    Activations Density 0.002%

    No Known Activations