© 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. 170387
    Prev
    Next
    INDEX
    Explanations

    Google, funding, list, White House, Love

    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
    困难
    0.47
    某些
    0.45
    Lots
    0.45
     সম্ভাবনা
    0.43
    统治
    0.42
    Spect
    0.42
    С
    0.41
    Causes
    0.41
     Lots
    0.41
    方法
    0.40
    POSITIVE LOGITS
     catering
    0.46
    ongono
    0.46
    िना
    0.46
    SubDirectory
    0.46
     delivering
    0.45
    itabbo
    0.45
     alleviating
    0.44
     ソ
    0.44
    er
    0.44
    atang
    0.44
    Activations Density 0.012%

    No Known Activations