© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-65K
    7. 1434
    Prev
    Next
    INDEX
    Explanations

    important followed by qualifying text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_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
    ombie
    1.51
     vorg
    1.46
     मोठे
    1.38
     platz
    1.36
     erste
    1.36
    어
    1.35
    뚝
    1.34
    티
    1.33
    ruvate
    1.33
    થમ
    1.33
    POSITIVE LOGITS
     indietro
    1.81
     एकदा
    1.74
    に戻
    1.55
     regained
    1.52
     复
    1.51
     reverted
    1.51
    វិញ
    1.50
     กลับ
    1.49
    eled
    1.48
    overy
    1.47
    Activations Density 0.484%

    No Known Activations