© 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. 83857
    Prev
    Next
    INDEX
    Explanations

    keys and identifiers

    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
    立方
    0.45
    的操作
    0.41
    낚
    0.39
     reconciliation
    0.39
     স্ন
    0.38
    产品的
    0.37
    Composer
    0.37
    Composable
    0.36
    cub
    0.36
    夹
    0.35
    POSITIVE LOGITS
    ossed
    0.46
     bb
    0.45
     ose
    0.43
    hjust
    0.42
     discontinue
    0.41
     puh
    0.40
     Procurement
    0.40
     USED
    0.39
    psum
    0.39
     darunter
    0.39
    Activations Density 0.002%

    No Known Activations