© 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. 381
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     reaffirm
    0.96
     Vereinig
    0.91
     grocery
    0.91
     pediatric
    0.91
     uncompromising
    0.83
    𝚈
    0.80
     overshadow
    0.79
     comedic
    0.79
     karaoke
    0.79
     مساعد
    0.79
    POSITIVE LOGITS
    6
    1.14
    2
    1.09
    5
    1.05
    8
    1.05
    1
    0.99
    3
    0.99
    0
    0.97
    7
    0.96
    。
    0.92
    4
    0.91
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.