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. 31-GEMMASCOPE-2-RES-262K
    4. 11876
    Prev
    Next
    INDEX
    Explanations

    are followed by descriptions

    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
     a
    0.82
    ו
    0.78
    ع
    0.77
     an
    0.75
     yake
    0.74
     którego
    0.71
     έχει
    0.69
     kojem
    0.69
     quale
    0.67
     która
    0.67
    POSITIVE LOGITS
     themselves
    0.79
     are
    0.60
    ari
    0.59
    wolves
    0.57
    oles
    0.56
    h
    0.55
    eli
    0.54
    rentices
    0.52
    ड्स
    0.50
    SCs
    0.50
    Activations Density 0.200%

    No Known Activations