© 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. 205624
    Prev
    Next
    INDEX
    Explanations

    estimating pose and building maps

    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
    關注
    0.45
    ademia
    0.40
     anbef
    0.40
    推薦
    0.39
    推奨
    0.38
    飜
    0.38
     herald
    0.38
    手册
    0.37
     recomenda
    0.37
     recomend
    0.37
    POSITIVE LOGITS
    ỗ
    0.44
    मोबाइल
    0.43
     метал
    0.43
     Gender
    0.42
    モバイル
    0.42
    Milk
    0.41
     Sanitation
    0.41
     Malware
    0.41
    Soil
    0.40
     Encryption
    0.39
    Activations Density 0.000%

    No Known Activations