© 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. 12402
    Prev
    Next
    INDEX
    Explanations

    greater than

    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
    
    0.64
    以及
    0.61
    applic
    0.61
    accum
    0.61
    沢山
    0.61
    ในการ
    0.60
    冒
    0.60
    और
    0.59
    filtr
    0.59
    그리고
    0.59
    POSITIVE LOGITS
     resembling
    0.81
     sterk
    0.79
     Öffentlich
    0.76
     zeer
    0.75
     eerst
    0.74
     ongeveer
    0.74
     nije
    0.73
     semelhante
    0.73
     serupa
    0.72
     négy
    0.72
    Activations Density 0.127%

    No Known Activations