© 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. 176514
    Prev
    Next
    INDEX
    Explanations

    determiner followed by noun

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

    system, lightly, length, team

    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
     Adjustment
    0.52
    お金
    0.48
    Harper
    0.46
    icited
    0.45
    Przy
    0.45
    diameter
    0.45
    sans
    0.44
    お客
    0.44
    н
    0.44
     Bourgoin
    0.44
    POSITIVE LOGITS
     escalera
    0.60
     habitación
    0.59
     diseño
    0.57
     ní
    0.51
     información
    0.50
     manera
    0.50
     electrón
    0.50
     recepción
    0.50
     línea
    0.50
     abajo
    0.50
    Activations Density 0.000%

    No Known Activations