© 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. 28406
    Prev
    Next
    INDEX
    Explanations

    experiences vs things

    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
    veloped
    0.46
    (",");
    0.45
    waved
    0.43
     ა
    0.43
     showered
    0.43
    나가
    0.43
    mapped
    0.43
    かが
    0.42
    nada
    0.42
     বিষয়
    0.42
    POSITIVE LOGITS
     appendix
    0.49
    itational
    0.46
     इंपॉर्टेंट
    0.44
     sonhos
    0.43
     महत्
    0.42
    弘
    0.42
    で行
    0.42
    Ꮠ
    0.42
     IMPORTANT
    0.41
     participle
    0.41
    Activations Density 0.005%

    No Known Activations