© 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. 14724
    Prev
    Next
    INDEX
    Explanations

    this is

    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
     lay
    1.44
    par
    1.39
     Olympus
    1.36
     Socrates
    1.34
    وكب
    1.32
     Par
    1.31
    cols
    1.30
    珑
    1.30
     Sorg
    1.29
     par
    1.28
    POSITIVE LOGITS
     காவல
    1.54
     scur
    1.53
     trampled
    1.51
    ুদ
    1.51
    iamiento
    1.49
    ()">
    1.47
    usura
    1.47
    èt
    1.44
     damper
    1.42
     मिलीमीटर
    1.42
    Activations Density 0.014%

    No Known Activations