© 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-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 8814
    Prev
    Next
    INDEX
    Explanations

    combining modalities and concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_17_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     prefixes
    0.83
     Choir
    0.80
     prefix
    0.80
     Particip
    0.78
     Their
    0.77
     their
    0.77
     ces
    0.76
     deres
    0.75
     Их
    0.74
    "><!--
    0.74
    POSITIVE LOGITS
    together
    0.89
    alike
    0.84
    power
    0.83
    パワー
    0.78
    са
    0.76
    kul
    0.75
     одновременно
    0.74
    ence
    0.73
    combination
    0.73
    Id
    0.73
    Activations Density 0.204%

    No Known Activations