© 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. 2064
    Prev
    Next
    INDEX
    Explanations

    question marks and Korean words

    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
     (“
    2.33
     („
    2.17
    (!
    2.11
     (‘
    2.09
    /(
    2.09
     («
    2.05
    (!)
    2.03
     (&
    2.02
     (
    2.02
     (>
    2.01
    POSITIVE LOGITS
     uh
    2.24
     Yeah
    2.17
     Mhm
    2.17
     yeah
    2.16
     그러면은
    2.02
     보면은
    1.93
     gonna
    1.84
     えっと
    1.81
     cuz
    1.78
     Okay
    1.75
    Activations Density 0.777%

    No Known Activations