© 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. 7-GEMMASCOPE-2-RES-16K
    7. 1636
    Prev
    Next
    INDEX
    Explanations

    government operatives, agents, and consultants

    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
    ā
    1.83
    ē
    1.68
    ādi
    1.62
    āra
    1.52
    uman
    1.49
    ān
    1.49
    āb
    1.48
    human
    1.46
    airan
    1.41
    𝗼
    1.41
    POSITIVE LOGITS
    ನನ್ನು
    1.77
    ி
    1.72
    BRANCH
    1.70
    ה
    1.67
    ಿಯನ್ನು
    1.62
    moveTo
    1.61
     LikeLike
    1.60
     pensée
    1.59
    Droite
    1.59
    ಿ
    1.59
    Activations Density 0.222%

    No Known Activations