© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13814
    Prev
    Next
    INDEX
    Explanations

    enough, sufficient, adequate

    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
    Negative Logits
     caminho
    0.64
    很多的
    0.64
    很多
    0.62
    ంది
    0.61
     trùng
    0.61
    적인
    0.61
     unnecessary
    0.58
    <h2>
    0.58
     luar
    0.56
    に向
    0.55
    POSITIVE LOGITS
     Adequate
    1.05
     Sufficient
    1.04
     amply
    0.97
     suffices
    0.90
    呛
    0.85
    Ade
    0.84
     ausreichend
    0.83
     adequate
    0.82
     ample
    0.82
     suffice
    0.82
    Activations Density 0.096%

    No Known Activations