© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 71855
    Prev
    Next
    INDEX
    Explanations

    generating random operations

    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
     \
    0.43
    word
    0.42
    otonic
    0.39
    0.39
    genic
    0.38
     Algonquin
    0.38
    ↵↵
    0.38
    ing
    0.38
     Sikkim
    0.38
     word
    0.37
    POSITIVE LOGITS
    स्फोट
    0.50
    𝒆
    0.50
    ար
    0.49
    <unused323>
    0.47
    ედერ
    0.47
    هران
    0.46
    त्मा
    0.46
    িদ্ধ
    0.46
    샅
    0.46
    <unused249>
    0.45
    Activations Density 0.006%

    No Known Activations