© 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. 101
    Prev
    Next
    INDEX
    Explanations

    listing elements

    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
     কর্তৃক
    1.44
    '_{\
    1.34
    ệ
    1.28
    }_{{\
    1.26
     විසින්
    1.26
    த்துள்ள
    1.25
    ṓ
    1.25
    _{{\
    1.24
     등으로
    1.24
    함으로써
    1.24
    POSITIVE LOGITS
     horrible
    1.45
     haha
    1.44
     stupid
    1.41
     kinda
    1.39
     yeah
    1.38
     crappy
    1.37
     wow
    1.36
     shitty
    1.35
     dude
    1.35
     hahaha
    1.34
    Activations Density 2.985%

    No Known Activations