© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 77092
    Prev
    Next
    INDEX
    Explanations

    However, contrastive conjunctions

    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_31_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
    iją
    0.64
     каждом
    0.59
    acyjnego
    0.57
    𝗡
    0.55
    シャフト
    0.54
     każdego
    0.52
     ܗܘ
    0.52
    IllegalArgument
    0.52
    Carousel
    0.52
    ಿಸಿದ್ದಾರೆ
    0.52
    POSITIVE LOGITS
     The
    0.61
     By
    0.54
     As
    0.50
     b
    0.50
     Cracked
    0.50
     Smiles
    0.50
     What
    0.49
     Winds
    0.49
     With
    0.49
     chow
    0.48
    Activations Density 0.004%

    No Known Activations