© 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. 5773
    Prev
    Next
    INDEX
    Explanations

    key differences

    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
    s
    1.35
    ries
    1.20
    …
    1.06
    ...
    1.04
    hets
    0.98
    简历
    0.95
    re
    0.93
    ise
    0.93
    ate
    0.92
    y
    0.91
    POSITIVE LOGITS
     AdapterView
    1.37
     oggetto
    1.36
    OrEqualTo
    1.33
    វេល
    1.32
    ូច
    1.28
    targetContext
    1.27
     IBOutlet
    1.26
    PrefabInstance
    1.26
     Subset
    1.25
     cogniz
    1.25
    Activations Density 0.007%

    No Known Activations