© 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. 13506
    Prev
    Next
    INDEX
    Explanations

    kernel drivers and modules

    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
    t
    2.72
    y
    1.48
    ,
    1.46
    ка
    1.36
    i
    1.17
    d
    1.16
    n
    1.16
    tive
    1.11
    اری
    1.10
    ко
    1.09
    POSITIVE LOGITS
     kernel
    1.20
    い
    1.13
    า
    1.13
    يت
    1.12
    س
    1.04
    Đi
    1.02
    লিখিত
    1.02
    سي
    1.01
     Kernel
    0.98
     أبريل
    0.98
    Activations Density 0.009%

    No Known Activations