© 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. 532
    Prev
    Next
    INDEX
    Explanations

    understand concepts and nuances

    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
    亦
    1.02
    encore
    0.96
     Prague
    0.95
    すら
    0.94
     Glory
    0.93
    也被
    0.89
     Moroz
    0.88
    颂
    0.88
     Seoul
    0.88
     restarted
    0.87
    POSITIVE LOGITS
     parameters
    1.54
     criteria
    1.47
     characteristics
    1.45
    characteristics
    1.39
     vulnerabilities
    1.36
     bottlenecks
    1.34
     weaknesses
    1.32
     strengths
    1.32
    Characteristics
    1.31
     variables
    1.30
    Activations Density 1.855%

    No Known Activations