© 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. 12481
    Prev
    Next
    INDEX
    Explanations

    introducing advice

    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
    期望
    1.51
    ributions
    1.49
     ismi
    1.48
    銘
    1.46
    𝒌
    1.46
     intereses
    1.45
    爱情
    1.42
    𝒎
    1.42
    的历史
    1.41
     исторических
    1.40
    POSITIVE LOGITS
    工作室
    1.43
     prototyping
    1.41
     mock
    1.36
     shoot
    1.36
     prototype
    1.36
     audition
    1.34
     photoshoot
    1.34
     cramped
    1.34
     scouting
    1.27
     연습
    1.27
    Activations Density 0.630%

    No Known Activations