© 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. 10880
    Prev
    Next
    INDEX
    Explanations

    asking "can you tell me"

    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
    actin
    1.75
    awatt
    1.64
     hanging
    1.62
    Attk
    1.61
    𝚊
    1.59
    penguin
    1.54
    hanging
    1.52
     annoyance
    1.49
    converted
    1.46
    сек
    1.46
    POSITIVE LOGITS
     horizonte
    1.10
    ي
    1.09
    bereitung
    1.09
     வரை
    1.08
     skład
    1.04
    eit
    1.03
    ণ্ট
    1.03
    śmy
    1.03
    ت
    1.03
    ここで
    1.02
    Activations Density 0.001%

    No Known Activations