© 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. 765
    Prev
    Next
    INDEX
    Explanations

    examples, unique, just

    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
    Safety
    1.53
    Notifier
    1.53
    atten
    1.49
    গি
    1.49
    ґ
    1.44
     atte
    1.41
     estre
    1.41
     aerial
    1.39
    isia
    1.39
    agai
    1.38
    POSITIVE LOGITS
     Kraj
    1.63
    嵬
    1.56
    فه
    1.35
     Bagan
    1.34
     RBS
    1.28
    Jdk
    1.27
    像
    1.27
    pond
    1.27
     रोक
    1.26
     Temple
    1.25
    Activations Density 0.000%

    No Known Activations