© 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. 14162
    Prev
    Next
    INDEX
    Explanations

    song bridges

    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
    ﻕ
    2.44
    constexpr
    2.06
    センチ
    1.81
    Around
    1.80
    waite
    1.76
     Wärme
    1.75
     ज़्यादा
    1.73
    ㎞
    1.72
    热
    1.71
    Հ
    1.71
    POSITIVE LOGITS
     citrate
    1.79
     wahr
    1.79
     abortion
    1.75
     negative
    1.71
     fung
    1.70
     predators
    1.69
     BBB
    1.67
     FDA
    1.67
     traum
    1.64
     penetrates
    1.64
    Activations Density 0.021%

    No Known Activations