© 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. 15974
    Prev
    Next
    INDEX
    Explanations

    numeric ordinals followed by time

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

    Gemma currently

    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
    ў
    0.43
    у
    0.40
    can
    0.40
    assigned
    0.39
    рави
    0.39
    would
    0.38
    пах
    0.38
     Lina
    0.37
    lli
    0.37
    .
    0.36
    POSITIVE LOGITS
     sposob
    0.38
    꾹
    0.38
     دیکھتے
    0.37
     complicado
    0.37
     rationalize
    0.37
     শুধুমাত্র
    0.37
     sólido
    0.37
     wechseln
    0.37
    ressive
    0.36
     nervioso
    0.36
    Activations Density 0.149%

    No Known Activations