© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 19346
    Prev
    Next
    INDEX
    Explanations

    24/7 availability

    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
    一夜
    0.42
     awaken
    0.40
     yester
    0.39
     awakening
    0.38
     joe
    0.38
     nights
    0.37
     udal
    0.37
    ឿ
    0.36
     bygone
    0.36
     year
    0.36
    POSITIVE LOGITS
    协助
    0.50
     δυνατό
    0.42
     booth
    0.41
    chatbot
    0.39
    協助
    0.39
    ですので
    0.39
    מיני
    0.38
    Suggest
    0.37
     черно
    0.37
    在全球
    0.37
    Activations Density 0.001%

    No Known Activations