© 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. 36118
    Prev
    Next
    INDEX
    Explanations

    sequence or focus

    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
     pants
    0.49
    ן
    0.45
     span
    0.43
     ज़र
    0.43
    PARTMENT
    0.43
    w
    0.43
     gain
    0.42
     undergo
    0.42
     saddle
    0.42
     ஓர்
    0.41
    POSITIVE LOGITS
     그다음에
    0.47
     Fokus
    0.46
    кугӀ
    0.45
     क्षतिग्रस्त
    0.43
    এরপর
    0.43
    amatsu
    0.43
    _{+}$
    0.42
     ardından
    0.42
     meskipun
    0.42
     केंद्रित
    0.42
    Activations Density 0.002%

    No Known Activations