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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 14150
    Prev
    Next
    INDEX
    Explanations

    ban or banning

    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
    indel
    2.69
    onsen
    2.54
    .\"
    2.51
    equ
    2.49
    ."[
    2.42
    \"
    2.39
    "।
    2.36
     idling
    2.33
     ralent
    2.31
     impl
    2.31
    POSITIVE LOGITS
    ンダント
    2.80
    𝑒
    2.80
    ږ
    2.78
    ças
    2.49
    𝑠
    2.39
    irteen
    2.37
    ړي
    2.36
     نواز
    2.31
    ished
    2.29
     केमिस्ट्री
    2.28
    Activations Density 0.013%

    No Known Activations