© 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. 72154
    Prev
    Next
    INDEX
    Explanations

    past last three games

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

    breakdown of why

    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
    捉
    0.48
    臤
    0.48
     ہوجائیں
    0.46
    地点
    0.45
    ｏ
    0.45
    現在
    0.44
    step
    0.43
     svého
    0.42
    市長
    0.42
    接待
    0.42
    POSITIVE LOGITS
     Cree
    0.48
     причине
    0.45
     здравоохра
    0.44
     Domains
    0.43
    8
    0.43
     دینی
    0.43
    ServiceModel
    0.43
     উভয়ে
    0.42
     Nxb
    0.41
     Scholarship
    0.41
    Activations Density 0.002%

    No Known Activations