© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 1975
    Prev
    Next
    INDEX
    Explanations

    `++i` in loops

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     codified
    1.88
     stamps
    1.83
     noun
    1.81
     Außen
    1.79
     brushes
    1.77
     sensation
    1.77
    的
    1.74
     nouns
    1.74
     grunn
    1.74
     Bour
    1.73
    POSITIVE LOGITS
     возраст
    0.95
    обходимо
    0.93
    윕
    0.81
    fluence
    0.81
    }})^{
    0.78
    鹧
    0.76
    вести
    0.73
    ramid
    0.73
     ہوسکتا
    0.73
    滚动
    0.73
    Activations Density 0.020%

    No Known Activations