© 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. 1464
    Prev
    Next
    INDEX
    Explanations

    cost and competition

    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
    न्नाथ
    0.48
    ন্দ্র
    0.47
     архів
    0.46
    Ň
    0.43
     أيض
    0.42
    lyPlugin
    0.42
    ۊ
    0.42
    ≣
    0.42
    ेंटिस
    0.41
     remedies
    0.41
    POSITIVE LOGITS
    pa
    0.42
    uses
    0.39
    if
    0.38
    CHANGED
    0.38
     Alcohol
    0.38
    Хо
    0.38
    ka
    0.37
    ','')
    0.37
    pad
    0.36
    switch
    0.36
    Activations Density 0.000%

    No Known Activations