© 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
    2. Gemma-3-1B
    3. 7-GEMMASCOPE-2-RES-16K
    4. 872
    Prev
    Next
    INDEX
    Explanations

    exercise and its benefits

    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
    american
    1.56
     american
    1.47
     rele
    1.45
    exam
    1.43
    。</
    1.42
     nant
    1.36
    caya
    1.31
     Arrange
    1.30
     American
    1.29
     kvalitet
    1.28
    POSITIVE LOGITS
    埶
    1.71
    めっちゃ
    1.67
    ńsk
    1.66
    めちゃ
    1.66
    ৭০
    1.59
    ৩৬
    1.57
    <unused2222>
    1.56
    ଲା
    1.56
     எதிர்க்க
    1.56
     переста
    1.56
    Activations Density 0.298%

    No Known Activations