Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 30482
    Prev
    Next
    INDEX
    Explanations

    continuous or sustained states

    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
    themealdb
    0.39
    赃
    0.38
    EME
    0.38
    ေါ
    0.38
    ໃຈ
    0.37
     verder
    0.37
    ڎ
    0.36
    豪華
    0.35
    OptionPane
    0.34
    тари
    0.34
    POSITIVE LOGITS
     continuous
    2.44
     continuously
    2.31
     постоян
    2.23
    continuous
    2.20
     sürekli
    2.20
     Continuous
    2.17
    Continuous
    2.16
     постоянно
    2.16
     constant
    2.14
     пості
    2.13
    Activations Density 0.045%

    No Known Activations