© 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. 7-GEMMASCOPE-2-RES-16K
    7. 2215
    Prev
    Next
    INDEX
    Explanations

    oxygen and width/height/display

    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_7_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
    िरिक्स
    1.92
    <unused1203>
    1.87
     Jednak
    1.86
    <unused2059>
    1.84
     MDLVertex
    1.83
     HashSet
    1.81
     InputMaybe
    1.79
    둣
    1.79
    MacroExpansion
    1.79
     IncludeField
    1.78
    POSITIVE LOGITS
    how
    1.81
    How
    1.47
     used
    1.46
     designed
    1.43
     to
    1.36
    used
    1.35
    如何
    1.33
     created
    1.32
     for
    1.31
     could
    1.31
    Activations Density 0.214%

    No Known Activations