© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 91
    Prev
    Next
    INDEX
    Explanations

    Inter Milan, history, celebrity

    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
    butadiene
    1.77
    inscription
    1.59
    стрі
    1.54
    orrh
    1.54
    echo
    1.52
    žić
    1.47
    ſ
    1.47
    economic
    1.47
    čet
    1.44
    ἔ
    1.43
    POSITIVE LOGITS
     робо
    1.23
     Dots
    1.22
     Person
    1.21
     FAN
    1.20
    น่า
    1.18
     кого
    1.18
    nya
    1.15
    น์
    1.14
     tight
    1.14
     yok
    1.13
    Activations Density 0.000%

    No Known Activations