© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 14052
    Prev
    Next
    INDEX
    Explanations

    making a choice

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

    attributes and descriptions

    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
    寛
    0.44
     exclusivamente
    0.43
    与之
    0.42
     исключительно
    0.40
     exclusivement
    0.40
    BoolVar
    0.40
    Surprisingly
    0.40
    axon
    0.38
    izarre
    0.38
     অপ্রত্যাশিত
    0.38
    POSITIVE LOGITS
    ).
    0.47
     was
    0.45
    すぐに
    0.44
     by
    0.43
    。
    0.43
     tincidunt
    0.43
     were
    0.42
    רי
    0.42
     additional
    0.41
     pola
    0.39
    Activations Density 0.141%

    No Known Activations