© 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. 108787
    Prev
    Next
    INDEX
    Explanations

    prepositions and connectors

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

    seasoning and salt to taste

    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
     eenvoud
    0.50
    か
    0.48
     instruct
    0.47
     instructs
    0.47
     terecht
    0.47
     prots
    0.46
     ideia
    0.46
     animator
    0.46
     инструк
    0.46
     empezar
    0.45
    POSITIVE LOGITS
    Peso
    0.49
    sí
    0.47
     Weight
    0.45
     Stellen
    0.45
    u
    0.45
    ".
    0.43
    grunge
    0.43
    uts
    0.43
    swedish
    0.43
    võ
    0.43
    Activations Density 0.001%

    No Known Activations