© 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. 12727
    Prev
    Next
    INDEX
    Explanations

    positive emojis

    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
    ...!
    0.39
    是非常
    0.36
    กรณ์
    0.35
    娓
    0.35
    i
    0.35
    !--
    0.35
    นะครับ
    0.35
    право
    0.34
    ignment
    0.34
    ୪
    0.34
    POSITIVE LOGITS
    ين
    0.36
    ة
    0.36
     meeste
    0.35
    ну
    0.34
     pinpoint
    0.33
     كانت
    0.33
     cuối
    0.32
     cụ
    0.32
    ]
    0.32
    ް
    0.32
    Activations Density 0.023%

    No Known Activations