© 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. 5348
    Prev
    Next
    INDEX
    Explanations

    romance, boldness, narratives, pasta

    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
    奈良
    0.70
     TABLE
    0.69
     Cerebral
    0.68
     백
    0.66
     武田
    0.66
    英語版
    0.65
    вания
    0.65
    цева
    0.64
    抟
    0.64
    著者
    0.64
    POSITIVE LOGITS
    s
    0.89
    នៅលើ
    0.86
    此同时
    0.84
    u
    0.82
    dı
    0.80
    msg
    0.79
     ljudi
    0.78
     brazen
    0.77
    t
    0.77
     blatant
    0.77
    Activations Density 0.002%

    No Known Activations