© 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. 182579
    Prev
    Next
    INDEX
    Explanations

    world map and saving

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

    medical and technical terminology

    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
     סי
    0.49
     காற்றின்
    0.49
     retroactive
    0.49
     shameless
    0.49
     வெளிப்புற
    0.48
    ן
    0.48
     vague
    0.47
     רו
    0.47
     חיצוני
    0.47
     confund
    0.46
    POSITIVE LOGITS
    #####
    0.50
    それぞれの
    0.49
    okban
    0.46
    欧
    0.46
    Ok
    0.45
    بد
    0.45
    捌
    0.45
    邦
    0.43
    ロシア
    0.43
     Eugenia
    0.43
    Activations Density 0.000%

    No Known Activations