© 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. 134168
    Prev
    Next
    INDEX
    Explanations

    description of specific items

    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
    俩
    0.41
    Medieval
    0.41
    arası
    0.40
     nicest
    0.40
    بيوتر
    0.39
    deux
    0.39
     théâtre
    0.39
    >(_
    0.38
    рьох
    0.38
    ʷ
    0.38
    POSITIVE LOGITS
     Installations
    0.47
    缺点
    0.46
     Relevance
    0.44
     Observations
    0.40
     HPLC
    0.39
    激光
    0.39
     файлов
    0.39
     Supporters
    0.39
     Radioactive
    0.38
     sungai
    0.38
    Activations Density 0.008%

    No Known Activations