© 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. 93923
    Prev
    Next
    INDEX
    Explanations

    cultural Marxism, spiral, innovative, signal, timelines

    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
    ד
    0.53
    Р
    0.49
    Э
    0.47
    а
    0.45
    Д
    0.45
    ל
    0.45
    Similar
    0.44
    ਤ
    0.44
    Exit
    0.44
    П
    0.44
    POSITIVE LOGITS
     (!)
    0.45
     Coca
    0.44
     éviter
    0.43
     McDonalds
    0.43
     Thin
    0.42
     huile
    0.42
     Chanel
    0.41
     (!
    0.41
     prayer
    0.41
     trag
    0.41
    Activations Density 0.013%

    No Known Activations