© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 105741
    Prev
    Next
    INDEX
    Explanations

    medical and drug names

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

    wheeled humanoid

    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
     były
    0.48
    фа
    0.48
     turun
    0.46
     Tapi
    0.46
    quia
    0.45
     Khalil
    0.45
    凱
    0.45
    ohama
    0.45
    sony
    0.44
    desert
    0.44
    POSITIVE LOGITS
    然后在
    0.45
    向
    0.41
    asText
    0.41
     উপ
    0.40
     মেডিক্যাল
    0.40
     เนาะ
    0.39
    情况下
    0.39
    欱
    0.39
    滪
    0.39
     많은
    0.38
    Activations Density 0.001%

    No Known Activations