© 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-65K
    7. 28540
    Prev
    Next
    INDEX
    Explanations

    into giving or revealing

    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_65k_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
     disprove
    0.50
    ዖ
    0.49
     COMPANIES
    0.46
     quelli
    0.45
     نسبة
    0.45
    enschap
    0.44
     restructured
    0.44
    addKill
    0.44
     Preheat
    0.44
     প্রতিদ্বন্দ্ব
    0.43
    POSITIVE LOGITS
    trex
    0.50
     cracking
    0.46
     supplies
    0.45
     Von
    0.43
    EEG
    0.42
     نیٹ
    0.42
    g
    0.41
     Grey
    0.41
    G
    0.41
     farm
    0.40
    Activations Density 0.001%

    No Known Activations