© 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. 83963
    Prev
    Next
    INDEX
    Explanations

    words followed by prepositions or articles

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

    humans generally

    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
    endaftaran
    0.53
    but
    0.52
    k
    0.50
    il
    0.50
    n
    0.49
    acterial
    0.49
    xido
    0.49
    hd
    0.49
    j
    0.48
    que
    0.48
    POSITIVE LOGITS
     Energies
    0.50
     βρί
    0.43
    抠
    0.43
     koh
    0.43
     traversal
    0.42
    思
    0.42
     THREE
    0.41
     Newer
    0.41
     STA
    0.41
     cohomology
    0.41
    Activations Density 0.001%

    No Known Activations