© 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. 53042
    Prev
    Next
    INDEX
    Explanations

    initial information, event descriptions

    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
    Arquivo
    0.49
    ridges
    0.46
    visional
    0.45
    intre
    0.44
    ashore
    0.43
    ಎಸ್
    0.43
    <unused39>
    0.43
    :");
    0.43
     επα
    0.42
     と
    0.42
    POSITIVE LOGITS
    దిక
    0.47
     Results
    0.46
     Fruits
    0.46
     Recruitment
    0.45
     Problems
    0.43
     Owing
    0.43
    봤
    0.43
     Returns
    0.43
     resembled
    0.42
     bagay
    0.42
    Activations Density 0.003%

    No Known Activations