© 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. 293
    Prev
    Next
    INDEX
    Explanations

    numbers and list elements

    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
     Volvo
    0.57
    ,
    0.57
     rigorous
    0.56
    ),
    0.55
     their
    0.55
     उनका
    0.54
     frac
    0.54
    올
    0.54
     Zika
    0.53
     pence
    0.53
    POSITIVE LOGITS
     Außerdem
    0.73
    <0xAD>
    0.66
    ْت
    0.64
    onDestroy
    0.63
     يمكنك
    0.62
    <0xAE>
    0.61
     clickView
    0.61
    ัม
    0.61
     Puedes
    0.61
    鈕
    0.60
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.