© 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
    5. 53-GEMMASCOPE-2-RES-65K
    7. 1138
    Prev
    Next
    INDEX
    Explanations

    applicable countries

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

    explain topics

    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_53_width_65k_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
     البح
    0.53
    <0x87>
    0.48
    辺
    0.42
    Bg
    0.41
    阳
    0.41
     bubbling
    0.41
     บท
    0.41
    <unused64>
    0.39
    部件
    0.39
    BUFF
    0.39
    POSITIVE LOGITS
     Greater
    0.48
    Greater
    0.48
     Extremely
    0.45
     Gary
    0.42
     Choir
    0.42
     Tây
    0.41
    Gary
    0.41
     choir
    0.39
    greater
    0.38
     Interested
    0.38
    Activations Density 0.110%

    No Known Activations