© 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. 1029
    Prev
    Next
    INDEX
    Explanations

    MM, m, M variations and context

    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
     peroxidase
    2.80
    ivism
    2.67
    稞
    2.67
    দ্ম
    2.57
    ფილი
    2.50
     कैरेट
    2.46
     tossing
    2.43
    ruci
    2.42
    ‍♀️
    2.37
    ोला
    2.35
    POSITIVE LOGITS
    स्तिष्क
    3.18
    mmm
    3.07
     mẽ
    2.92
    ilitar
    2.90
    mmmm
    2.88
    üller
    2.87
    ędzy
    2.86
    बाईल
    2.80
    MMM
    2.73
    bius
    2.71
    Activations Density 4.003%

    No Known Activations