© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 10361
    Prev
    Next
    INDEX
    Explanations

    terraform providers

    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
     arbeitet
    0.31
     geschaffen
    0.30
     создает
    0.29
    的話
    0.29
     reconocido
    0.29
     ragazzo
    0.28
    誐
    0.28
    湟
    0.28
     дело
    0.28
    न्यास
    0.28
    POSITIVE LOGITS
     home
    0.28
     block
    0.28
    test
    0.27
     silent
    0.27
    Silent
    0.27
    silent
    0.26
     shard
    0.26
    Block
    0.25
    drive
    0.25
    '
    0.25
    Activations Density 0.000%

    No Known Activations