© 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. 3580
    Prev
    Next
    INDEX
    Explanations

    string interpolation #{ } or $( )

    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
    ا
    1.23
    ält
    1.18
    și
    1.11
    alen
    1.10
    zení
    1.10
    বয়
    1.08
    Len
    1.05
    र
    1.04
    Ten
    1.04
    şen
    1.04
    POSITIVE LOGITS
     插
    1.48
     マット
    1.47
     可以
    1.42
     右
    1.40
     美術
    1.39
     但
    1.35
     按
    1.35
     而且
    1.34
     又
    1.33
     很
    1.33
    Activations Density 0.004%

    No Known Activations