© 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. 83756
    Prev
    Next
    INDEX
    Explanations

    numbers, cryptocurrencies, and places

    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
    "],[
    0.61
     nadi
    0.48
    ール
    0.47
    緘
    0.46
     défendre
    0.45
    aprend
    0.45
    WithFieldContext
    0.44
     diferencias
    0.44
    راهيم
    0.43
    なかなか
    0.43
    POSITIVE LOGITS
    s
    0.54
    n
    0.46
    in
    0.43
    Supported
    0.42
     Govt
    0.41
     disclosures
    0.41
    বাহ
    0.41
     abutting
    0.41
     YAML
    0.40
    ).
    0.40
    Activations Density 0.001%

    No Known Activations