© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 5948
    Prev
    Next
    INDEX
    Explanations

    empty list

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_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
    n
    0.59
    也在
    0.56
    as
    0.55
    ialis
    0.55
    昰
    0.54
     effectivement
    0.52
    也被
    0.52
    ÕES
    0.51
    合并
    0.50
    اعدة
    0.50
    POSITIVE LOGITS
     or
    0.91
     или
    0.80
     অথবা
    0.71
     oppure
    0.71
     ή
    0.70
     หรือ
    0.70
     and
    0.66
     ամ
    0.66
     ogni
    0.65
    หรือ
    0.65
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.