© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 5146
    Prev
    Next
    INDEX
    Explanations

    comparing models and technologies

    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
    usd
    1.57
     breads
    1.41
    ussians
    1.36
    idus
    1.32
    osse
    1.32
     atoms
    1.31
    UserId
    1.25
    
    1.25
    錘
    1.24
    ၡ
    1.22
    POSITIVE LOGITS
     other
    1.48
    other
    1.26
     altra
    1.21
     anderen
    1.18
     altro
    1.17
    อื่น
    1.16
    อื่นๆ
    1.13
     другими
    1.12
     andere
    1.12
     another
    1.12
    Activations Density 0.147%

    No Known Activations