© 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. 16-GEMMASCOPE-2-RES-262K
    7. 142633
    Prev
    Next
    INDEX
    Explanations

    kinetic energy redirection

    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_16_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
     describing
    0.50
     touches
    0.50
    емся
    0.48
    ផ្នែក
    0.48
     မှာ
    0.47
    𝗅
    0.46
     kişinin
    0.46
     bahasa
    0.46
     отде
    0.45
     specialising
    0.45
    POSITIVE LOGITS
     Forest
    0.53
    伷
    0.50
     ovih
    0.48
     residents
    0.47
    Bold
    0.46
    Crist
    0.46
     Death
    0.46
    Forest
    0.46
     फॉरेस्ट
    0.46
     forest
    0.46
    Activations Density 0.000%

    No Known Activations