© 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. 95369
    Prev
    Next
    INDEX
    Explanations

    how do I get started

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

    economic and legal concepts

    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
    マー
    0.56
     rehab
    0.51
    ھی
    0.48
     Armor
    0.46
    シ
    0.46
    Armor
    0.44
    ቾ
    0.44
    rme
    0.42
     Rehab
    0.42
    Ꮇ
    0.42
    POSITIVE LOGITS
     menjel
    0.56
    高志森
    0.50
    拍摄
    0.48
     σύν
    0.47
     économique
    0.47
     økonom
    0.46
     Geschä
    0.45
     მაგრამ
    0.45
     그러
    0.44
     ekonom
    0.44
    Activations Density 0.001%

    No Known Activations