© 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. 210987
    Prev
    Next
    INDEX
    Explanations

    parents and guardianship context

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

    cause of, support it, substances when

    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
    ص
    0.51
    天
    0.44
    aya
    0.44
    为什么要
    0.42
     মাহমু
    0.40
    ariam
    0.40
    轴
    0.40
    ιου
    0.39
    to
    0.39
    成
    0.39
    POSITIVE LOGITS
     NCP
    0.58
    ၺ
    0.53
     inertia
    0.51
    hoog
    0.50
    НГ
    0.48
     істо
    0.48
    ᱔
    0.47
     híbr
    0.47
     iletişim
    0.47
     NCS
    0.46
    Activations Density 0.000%

    No Known Activations