© 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. 16-GEMMASCOPE-2-RES-262K
    7. 27401
    Prev
    Next
    INDEX
    Explanations

    IBM Cloud, AI, and offers

    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_16_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
     recon
    0.64
    "
    0.62
    recon
    0.61
     Recon
    0.61
     Amor
    0.60
    ic
    0.59
    ners
    0.59
    re
    0.59
    ig
    0.58
    ियों
    0.58
    POSITIVE LOGITS
    IBM
    0.79
     IBM
    0.74
     пост
    0.52
     SDGs
    0.50
     viciss
    0.50
     Audiodate
    0.50
    란
    0.49
    лада
    0.49
    いただけます
    0.49
     类型
    0.49
    Activations Density 0.037%

    No Known Activations