© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 8938
    Prev
    Next
    INDEX
    Explanations

    specialized vocabulary or concepts

    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_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
     Mendez
    0.56
     likely
    0.55
     counts
    0.54
     Django
    0.54
    सनीय
    0.54
     Intelligence
    0.53
    就好了
    0.52
    .”[
    0.51
     सच
    0.50
     politicians
    0.50
    POSITIVE LOGITS
    об
    0.59
    sentiment
    0.59
    זה
    0.57
    supplement
    0.57
    ነስ
    0.57
    ርዓ
    0.56
    teen
    0.56
    租赁
    0.55
    пель
    0.54
    提及
    0.54
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.