© 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. 200708
    Prev
    Next
    INDEX
    Explanations

    lineage, thrones, pressure, consistent

    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
     inducible
    0.50
    AsUpIndicator
    0.48
    設備
    0.48
     Semoga
    0.47
    的公司
    0.46
     খ্যা
    0.45
     recognises
    0.45
    ＾
    0.45
     Grazie
    0.45
     campaigning
    0.44
    POSITIVE LOGITS
    t
    0.52
     что
    0.50
    Six
    0.49
     и
    0.47
    y
    0.46
    PAN
    0.45
    six
    0.45
    FIX
    0.45
    Crypt
    0.45
     හා
    0.45
    Activations Density 0.004%

    No Known Activations