© 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. 58400
    Prev
    Next
    INDEX
    Explanations

    scheduled appointments, said to, public domain

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

    Dependabot

    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
    V
    0.48
    Vr
    0.47
    شناسی
    0.44
    ネットワーク
    0.44
    的值
    0.43
    Ķ
    0.43
    内置
    0.43
    VZ
    0.42
    工作
    0.41
    Quiet
    0.41
    POSITIVE LOGITS
    ừng
    0.55
    atat
    0.50
    will
    0.50
     ඉතා
    0.48
     عندما
    0.46
    exponential
    0.45
    </h2>
    0.45
    ໂດຍ
    0.45
     ഉയർന്ന
    0.45
     विनाश
    0.43
    Activations Density 0.000%

    No Known Activations