© 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. 16-GEMMASCOPE-2-RES-262K
    7. 3750
    Prev
    Next
    INDEX
    Explanations

    small adjustments

    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_16_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
     في
    1.16
    ك
    1.16
    يا
    1.14
    此同时
    1.13
    话
    1.10
    在
    1.09
    使用
    1.02
    kelijk
    1.01
    كار
    0.96
    في
    0.93
    POSITIVE LOGITS
    t
    1.70
    ت
    1.47
    т
    1.44
     for
    1.20
     flexion
    1.12
    त
    1.12
    تون
    1.08
     divulg
    1.04
    る
    1.03
    ل
    1.02
    Activations Density 0.041%

    No Known Activations