© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 41
    Prev
    Next
    INDEX
    Explanations

    how followed by explanation

    np_acts-logits-general · gemini-2.5-flash-lite

    how things work

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_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
     ngunit
    0.19
     如果
    0.18
     způ
    0.18
     ア
    0.18
     innehåller
    0.18
     त्यानंतर
    0.17
     ने
    0.17
     ،
    0.17
     alebo
    0.17
     jotka
    0.17
    POSITIVE LOGITS
    soever
    0.23
    an
    0.19
     it
    0.19
    cribes
    0.18
     this
    0.18
    то
    0.18
    this
    0.18
    it
    0.17
    much
    0.17
     живу
    0.17
    Activations Density 0.906%

    No Known Activations