© 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. 120669
    Prev
    Next
    INDEX
    Explanations

    mathematics and computing concepts

    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
    Warehouse
    0.43
     Mechanisms
    0.42
     ظل
    0.41
     Mechanism
    0.41
     everytime
    0.40
     Fulfillment
    0.40
    }`))
    0.40
    mechanism
    0.40
     totalSupply
    0.40
     наверное
    0.39
    POSITIVE LOGITS
    講
    0.44
     mic
    0.43
     ئەم
    0.39
     lich
    0.37
    㧋
    0.37
    ுக்
    0.36
     komm
    0.36
     fis
    0.36
     yn
    0.36
     rech
    0.35
    Activations Density 0.000%

    No Known Activations