© 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. 12-GEMMASCOPE-2-RES-16K
    7. 83
    Prev
    Next
    INDEX
    Explanations

    instructions for purposes

    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_12_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
    ي
    1.16
    y
    1.08
    ità
    0.98
    hos
    0.98
    ités
    0.97
    را
    0.97
    taus
    0.96
    dek
    0.95
    daten
    0.94
    elos
    0.94
    POSITIVE LOGITS
     comet
    1.02
     comer
    1.00
     pesticide
    0.94
     종
    0.86
     lop
    0.86
     wint
    0.86
     cr
    0.86
    你想
    0.86
     corridor
    0.86
    种
    0.86
    Activations Density 0.000%

    No Known Activations