© 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-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 6557
    Prev
    Next
    INDEX
    Explanations

    nuanced and nuances

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_22_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
     conectar
    0.98
     contributed
    0.91
    Contribution
    0.88
    تون
    0.85
     inaction
    0.84
    செய்ய
    0.84
    Upgradeable
    0.82
    නී
    0.82
     resistances
    0.81
    텃
    0.81
    POSITIVE LOGITS
    anced
    1.21
    clide
    1.20
    clides
    1.19
     hvor
    1.13
    ñez
    1.07
    iances
    1.04
    varande
    1.01
     EMG
    1.01
     ক্যাম্পে
    1.00
     DIS
    1.00
    Activations Density 0.021%

    No Known Activations