© 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. 17541
    Prev
    Next
    INDEX
    Explanations

    healthcare, LGBT, data, environmental issues

    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
    嗥
    0.47
    Bokeh
    0.42
     흰
    0.41
     நட்சத்திர
    0.40
    ilebilir
    0.40
    ốc
    0.39
    agonal
    0.39
    极
    0.39
    ulfanyl
    0.39
    자가
    0.38
    POSITIVE LOGITS
     creditors
    0.47
     financials
    0.47
     CEOs
    0.46
     entrepreneurs
    0.44
     corporate
    0.44
     alliances
    0.44
     economics
    0.42
     legitimacy
    0.42
     empresarios
    0.42
     finance
    0.42
    Activations Density 0.159%

    No Known Activations