© 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. 50514
    Prev
    Next
    INDEX
    Explanations

    Option 1 (Concise & Clear)

    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
     Firstly
    0.55
     firstly
    0.52
     primero
    0.50
    "]);
    0.48
    Firstly
    0.47
     ۱
    0.45
     اولا
    0.45
     primeiro
    0.45
    １
    0.44
     primera
    0.42
    POSITIVE LOGITS
    <blockquote>
    0.50
     म्हट
    0.39
    that
    0.39
    which
    0.39
    recogn
    0.37
     repeal
    0.37
    における
    0.37
    же
    0.37
    setKeepCallback
    0.37
    nsic
    0.36
    Activations Density 0.020%

    No Known Activations