© 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
    2. Gemma-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 108862
    Prev
    Next
    INDEX
    Explanations

    South Park scripts and robots

    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
     쇼
    0.51
     Krzysz
    0.50
     스토리
    0.49
    America
    0.48
    uvu
    0.47
     Jaya
    0.47
     Iya
    0.46
    IKV
    0.46
    Ꮢ
    0.46
     KV
    0.46
    POSITIVE LOGITS
    技能
    0.51
    нима
    0.47
    тере
    0.46
    lerdir
    0.46
    рии
    0.46
    erson
    0.45
    ாத
    0.45
    案
    0.44
    -
    0.43
     retinal
    0.43
    Activations Density 0.000%

    No Known Activations