© 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. 4826
    Prev
    Next
    INDEX
    Explanations

    list of

    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
    0.62
     marred
    0.61
     double
    0.60
     field
    0.57
    :
    0.57
     imply
    0.55
     continually
    0.55
     head
    0.54
     signifies
    0.54
     footage
    0.54
    POSITIVE LOGITS
    ᕝ
    0.67
    駐車場
    0.64
     وغیرہ
    0.61
    ∈
    0.61
    วันนี้
    0.60
    Bitmap
    0.59
    ቛ
    0.59
     บาท
    0.58
    कांग्रेस
    0.58
    राबरी
    0.58
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.