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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 14530
    Prev
    Next
    INDEX
    Explanations

    danger and risk

    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_16k_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
     То
    1.25
    ７
    1.17
     Но
    1.17
    愀
    1.17
     Сан
    1.16
     温
    1.16
     新
    1.15
    
    1.14
     Все
    1.14
     七
    1.13
    POSITIVE LOGITS
    ágico
    1.44
     delegado
    1.34
     mettere
    1.30
    afficher
    1.28
     verstär
    1.27
     offrent
    1.26
     ofrecen
    1.24
    recorder
    1.24
     realizzato
    1.23
    डु
    1.23
    Activations Density 0.000%

    No Known Activations