© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 87118
    Prev
    Next
    INDEX
    Explanations

    interactive visualization

    np_acts-logits-general · gemini-2.5-flash-lite

    audio-visual media or artist

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    忄
    0.51
    direccion
    0.49
     problème
    0.47
    手順
    0.46
     disgrace
    0.46
    followlike
    0.45
     ईमित्र
    0.44
    ometr
    0.44
    ineuses
    0.44
    initely
    0.43
    POSITIVE LOGITS
    核
    0.55
    拍卖
    0.54
     imagenes
    0.46
    VE
    0.46
     audiovisual
    0.45
     核
    0.45
     audiov
    0.42
     auctioned
    0.42
     besitzen
    0.42
    委托
    0.41
    Activations Density 0.002%

    No Known Activations