© 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. 32854
    Prev
    Next
    INDEX
    Explanations

    called when or every

    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
     using
    0.45
     Juga
    0.45
     تلك
    0.43
     Using
    0.43
     menggunakan
    0.43
     Rainy
    0.42
     Ambiental
    0.41
    ᓪ
    0.40
     ક્ષ
    0.40
     যাওয়ার
    0.39
    POSITIVE LOGITS
     ogni
    0.40
    quando
    0.40
    acles
    0.39
    хів
    0.38
     nondegenerate
    0.38
    体力
    0.38
    non
    0.38
     involution
    0.37
    飽
    0.37
    otid
    0.37
    Activations Density 0.021%

    No Known Activations