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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 12600
    Prev
    Next
    INDEX
    Explanations

    Single Responsibility Principle

    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
    schild
    3.33
    𝐲
    3.10
    ى
    3.09
    embangan
    2.94
    oster
    2.89
    𝐨
    2.84
    𝐮
    2.81
    धरी
    2.81
    tedir
    2.76
    𝐞
    2.76
    POSITIVE LOGITS
    ו
    3.22
    ழுகு
    2.98
     Old
    2.77
    데요
    2.72
    al
    2.64
    り
    2.62
    ℂ
    2.62
    ্ম্ম
    2.62
    i
    2.60
    けた
    2.58
    Activations Density 0.057%

    No Known Activations