© 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. 83724
    Prev
    Next
    INDEX
    Explanations

    code callbacks initialization

    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
    allowing
    0.43
    onces
    0.39
    IDENTAL
    0.38
     divisible
    0.37
     allowing
    0.36
    нару
    0.35
    }--
    0.34
    viol
    0.34
    factorial
    0.34
    Fun
    0.33
    POSITIVE LOGITS
     Awake
    0.45
    Appear
    0.42
    布局
    0.41
     Layout
    0.40
     Clayton
    0.40
    起床
    0.39
     wakeup
    0.39
    鞭
    0.38
     layout
    0.38
     sve
    0.38
    Activations Density 0.004%

    No Known Activations