© 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. 164160
    Prev
    Next
    INDEX
    Explanations

    wireless connection

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

    HTML structure and links

    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
     diminish
    0.50
    ophosph
    0.45
    咯
    0.45
    iswa
    0.45
    iselle
    0.44
     interruption
    0.42
    isku
    0.42
     prostaglandins
    0.42
    льд
    0.41
    interrupt
    0.41
    POSITIVE LOGITS
     Banyak
    0.57
     ভাবে
    0.50
    สมัคร
    0.49
    Гра
    0.49
    خواندن
    0.49
     Վ
    0.47
    blätter
    0.47
     אחד
    0.46
     მოს
    0.46
     たい
    0.45
    Activations Density 0.001%

    No Known Activations