© 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. 10032
    Prev
    Next
    INDEX
    Explanations

    character names

    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
     “
    1.56
     컨
    1.49
     跟
    1.37
     접
    1.32
     ПО
    1.32
     트
    1.31
     被
    1.31
     ✅
    1.30
     “‘
    1.30
     보유
    1.29
    POSITIVE LOGITS
    Jar
    1.31
    Vida
    1.24
    Jon
    1.23
    Chess
    1.23
     itulah
    1.23
    Flight
    1.22
    Dinner
    1.22
    Nada
    1.21
    Jonathan
    1.20
    Laboratory
    1.19
    Activations Density 0.024%

    No Known Activations