© 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
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 224439
    Prev
    Next
    INDEX
    Explanations

    transplanted, grafted, suppressed

    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_40_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
    諳
    0.42
     أول
    0.41
    ency
    0.41
    tik
    0.40
    chtigen
    0.40
    waiting
    0.40
     reminder
    0.40
    !">
    0.40
    wap
    0.39
    thirsty
    0.39
    POSITIVE LOGITS
     transplanted
    0.40
     Universidad
    0.38
     equally
    0.38
     transposed
    0.37
    AFD
    0.37
     VEGFR
    0.36
     grafted
    0.36
     GMA
    0.36
     suppressed
    0.35
     transplants
    0.35
    Activations Density 0.000%

    No Known Activations