© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 42999
    Prev
    Next
    INDEX
    Explanations

    list item structure with css styling

    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
    জ
    0.47
    癸
    0.42
     Kiy
    0.41
     Collecting
    0.41
    ារ
    0.40
    به
    0.40
    ຕ
    0.39
    ზ
    0.39
     Japón
    0.39
     ক্লে
    0.39
    POSITIVE LOGITS
     rib
    0.40
    คาเดมี
    0.38
     ListItem
    0.37
     anagram
    0.37
    鈥
    0.37
     restaurante
    0.36
    andidates
    0.36
     hvert
    0.36
     probes
    0.35
    inition
    0.35
    Activations Density 0.012%

    No Known Activations