© 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. 257984
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    {
    0.58
    řed
    0.56
    ând
    0.55
    ⒏
    0.54
    LARGE
    0.53
    {-\
    0.53
    ংকে
    0.52
     путеше
    0.52
     إلي
    0.51
     optar
    0.51
    POSITIVE LOGITS
    ა
    0.76
    ap
    0.74
    A
    0.74
    i
    0.72
    ج
    0.69
    ف
    0.67
    िक
    0.66
     diikuti
    0.66
    ق
    0.65
    ின்
    0.65
    Activations Density 0.011%

    No Known Activations