© 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. 181660
    Prev
    Next
    INDEX
    Explanations

    numbers and years

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

    market trends, economic growth, or progression

    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
    k
    0.52
    ک
    0.50
    ב
    0.49
     Province
    0.48
    İ
    0.48
     dengan
    0.46
     sekitar
    0.46
     beim
    0.45
    ії
    0.45
     bazı
    0.45
    POSITIVE LOGITS
    arul
    0.51
    锼
    0.47
    ettet
    0.46
     rained
    0.42
     principalTable
    0.42
     considérer
    0.41
     ಅಥವಾ
    0.41
     ਜਾਂ
    0.41
    teg
    0.41
     কিংবা
    0.40
    Activations Density 0.001%

    No Known Activations