© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 111852
    Prev
    Next
    INDEX
    Explanations

    fill in brackets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    🤴
    0.40
    នៅក្នុង
    0.40
     braces
    0.39
    മാണ
    0.39
    вью
    0.39
    富
    0.38
    inside
    0.38
    ittä
    0.37
    ᐃ
    0.37
    אַר
    0.37
    POSITIVE LOGITS
    ed
    0.49
     AUTO
    0.45
    owana
    0.41
     masked
    0.40
     Stadium
    0.39
     Equipped
    0.39
     figure
    0.39
     Format
    0.39
     Figure
    0.39
     clad
    0.38
    Activations Density 0.008%

    No Known Activations