© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 117578
    Prev
    Next
    INDEX
    Explanations

    phrases like "by depositing" or "(Brent)"

    np_acts-logits-general · gemini-2.5-flash-lite

    medical and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anha
    0.46
    磴
    0.45
    天上
    0.43
    祝福
    0.43
    礼
    0.41
     তী
    0.41
     itt
    0.41
     mumbai
    0.41
     becomes
    0.40
    廚
    0.40
    POSITIVE LOGITS
     خشک
    0.48
     Angaben
    0.48
     Lactobacillus
    0.45
     पड़े
    0.44
     эффек
    0.44
     рациона
    0.44
     Shetland
    0.44
     lượng
    0.43
    propan
    0.43
     Omicron
    0.43
    Activations Density 0.001%

    No Known Activations