© 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. 170352
    Prev
    Next
    INDEX
    Explanations

    Ukraine war, rice paddies, microwave

    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
    льных
    0.60
     экономических
    0.50
    ز
    0.49
    тических
    0.48
    тельных
    0.47
    ਰ
    0.46
    ъ
    0.46
    汚
    0.46
    پ
    0.45
    కు
    0.45
    POSITIVE LOGITS
     অবিশ্বাস্য
    0.51
     Miners
    0.46
     Puente
    0.42
     tributes
    0.42
     anti
    0.41
     NHS
    0.41
     Minecraft
    0.41
     Jiang
    0.40
     Harley
    0.40
     alternatives
    0.40
    Activations Density 0.007%

    No Known Activations