© 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. 13855
    Prev
    Next
    INDEX
    Explanations

    ESPN sports links

    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
    いた
    3.33
     земель
    2.84
    ᑕ
    2.80
    Ꮳ
    2.77
    trends
    2.70
    ㅛ
    2.67
    smöglichkeiten
    2.62
    Transl
    2.61
     جمهوری
    2.60
    testen
    2.57
    POSITIVE LOGITS
    ي
    4.70
    ות
    3.74
    ar
    3.71
    ের
    3.66
    or
    3.59
    an
    3.59
    м
    3.36
    л
    3.35
    ו
    3.30
    en
    3.24
    Activations Density 0.019%

    No Known Activations