© 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. 2039
    Prev
    Next
    INDEX
    Explanations

    who will win

    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
    ց
    3.04
    
    2.86
    ্শন
    2.71
    ంద్
    2.66
    χύ
    2.59
     flurry
    2.58
    ্ম্ম
    2.56
    ే
    2.53
    ＾
    2.51
    к
    2.47
    POSITIVE LOGITS
    𝙤
    2.76
    نگ
    2.64
    𝙩
    2.60
    ống
    2.47
     Verw
    2.45
    𝙧
    2.40
    𝙖
    2.37
    𝙡
    2.36
    ጨማሪ
    2.33
     drugim
    2.33
    Activations Density 0.000%

    No Known Activations