© 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. 801
    Prev
    Next
    INDEX
    Explanations

    code context

    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
     trở
    0.42
     phải
    0.40
    ,_-
    0.40
    BSData
    0.39
     Schedules
    0.39
     други
    0.38
     налого
    0.38
     așa
    0.38
     sẽ
    0.38
     printers
    0.38
    POSITIVE LOGITS
    0.54
     to
    0.40
    s
    0.38
    ian
    0.38
    o
    0.36
    การ
    0.36
    url
    0.35
    q
    0.34
    ne
    0.34
    บ
    0.34
    Activations Density 0.064%

    No Known Activations