© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 33017
    Prev
    Next
    INDEX
    Explanations

    descriptive words followed by nouns

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

    search, calculate, foster understanding

    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
    Not in Any Lists

    No Comments

    Negative Logits
     bè
    0.53
     yú
    0.52
     αντί
    0.51
     diffé
    0.50
     дії
    0.50
     म्हटले
    0.49
    扪
    0.49
     сьогодні
    0.48
     schéma
    0.48
     svět
    0.47
    POSITIVE LOGITS
    itemList
    0.44
     apartment
    0.43
    a
    0.42
     happiest
    0.42
    r
    0.42
     cruises
    0.42
     townhouse
    0.41
    ুপ
    0.41
     cuisines
    0.41
     配
    0.41
    Activations Density 0.000%

    No Known Activations