© 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. 38846
    Prev
    Next
    INDEX
    Explanations

    kernel or core

    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
    t
    0.41
     хочет
    0.41
    IANA
    0.40
    摂取
    0.39
     Tattha
    0.39
    お店
    0.38
     Scop
    0.38
     যাচাই
    0.38
    িকার
    0.38
    انی
    0.38
    POSITIVE LOGITS
    撞
    0.48
     కె
    0.47
    Keg
    0.46
     Keg
    0.45
     kernel
    0.44
     Kernel
    0.44
     keg
    0.44
     KELL
    0.44
     ケ
    0.42
    Kern
    0.40
    Activations Density 0.019%

    No Known Activations