© 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. 40676
    Prev
    Next
    INDEX
    Explanations

    common "Daily" phrases

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

    daily activities and content

    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
    ।
    0.59
     étage
    0.54
     Gül
    0.54
    ليل
    0.54
     Tekh
    0.54
     proactively
    0.54
    𝗚
    0.53
    lığ
    0.52
    İM
    0.52
     Utilisez
    0.52
    POSITIVE LOGITS
     Daily
    0.91
    Daily
    0.77
     daily
    0.76
    每日
    0.75
    DAILY
    0.74
    daily
    0.72
     ежеднев
    0.67
    c
    0.64
     डेली
    0.64
     दैनिक
    0.63
    Activations Density 0.029%

    No Known Activations