© 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. 21632
    Prev
    Next
    INDEX
    Explanations

    Rust thread and cell operations

    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
     serde
    0.45
     liber
    0.42
     serpentine
    0.41
    Liber
    0.39
    Turb
    0.39
     sier
    0.38
     å
    0.37
     près
    0.37
    гол
    0.37
    溢
    0.37
    POSITIVE LOGITS
     drop
    0.52
     Drop
    0.47
    Drop
    0.47
    Sender
    0.45
     Sender
    0.44
    dro
    0.43
     dropout
    0.43
     сообще
    0.42
     DROP
    0.42
    dropped
    0.41
    Activations Density 0.021%

    No Known Activations