© 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. 239811
    Prev
    Next
    INDEX
    Explanations

    prepositional phrases after articles

    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
     celebrates
    0.19
     and
    0.17
    리와
    0.17
    чики
    0.16
    -
    0.16
    BURY
    0.16
    нова
    0.16
    쟈
    0.16
    Invit
    0.15
    PAUL
    0.15
    POSITIVE LOGITS
     trivially
    0.22
     plausible
    0.21
     Riemannian
    0.20
     Hadamard
    0.20
     monotonically
    0.20
     Cauchy
    0.19
     Gaussian
    0.18
     Ignore
    0.18
     ArrayIndex
    0.18
     sqrt
    0.18
    Activations Density 0.026%

    No Known Activations