© 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. 19020
    Prev
    Next
    INDEX
    Explanations

    sections and lists

    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
    或许
    0.34
     ہوسکتا
    0.34
     _:
    0.32
    かもしれません
    0.32
    வோ
    0.32
     olabilir
    0.32
     parseFloat
    0.32
     año
    0.31
     asent
    0.31
    ப்பின
    0.31
    POSITIVE LOGITS
    chlor
    0.36
     lastly
    0.35
    Force
    0.34
     Tinggi
    0.33
     &
    0.32
    limit
    0.32
    Sweet
    0.31
    KEA
    0.31
    Chlor
    0.31
    𝗗
    0.31
    Activations Density 0.482%

    No Known Activations