© 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. 78271
    Prev
    Next
    INDEX
    Explanations

    cleaning, license, relationship, consumers, land

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

    taken, available, assuming

    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
     thành
    0.48
     đầy
    0.48
    getOrder
    0.48
    ᱐
    0.48
     kasnije
    0.47
     flannel
    0.46
    keun
    0.46
     хорошее
    0.46
     wearables
    0.46
     الحس
    0.45
    POSITIVE LOGITS
    会社
    0.45
    lr
    0.44
    lots
    0.44
    isters
    0.44
     Stelle
    0.44
    щиков
    0.44
     माहिती
    0.43
    娘
    0.43
    蘖
    0.43
     STER
    0.42
    Activations Density 0.002%

    No Known Activations