© 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. 14356
    Prev
    Next
    INDEX
    Explanations

    pseudoephedrine

    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
    s
    3.54
    ු
    2.66
    u
    2.56
    ો
    2.56
    t
    2.53
    sion
    2.46
    tions
    2.41
    tive
    2.31
    ি
    2.31
    ي
    2.23
    POSITIVE LOGITS
    ქვს
    1.76
     geleden
    1.66
    wheeled
    1.64
    𝙃
    1.63
    kh
    1.62
    ThreadPool
    1.62
    которые
    1.59
    apiKey
    1.58
    튜브
    1.56
    ग्विजय
    1.56
    Activations Density 0.059%

    No Known Activations