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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 1236
    Prev
    Next
    INDEX
    Explanations

    prepositional phrases starting with "in"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    '
    0.29
    ’
    0.29
    ↵
    0.24
    '(
    0.20
    ;
    0.19
     They
    0.19
     (
    0.19
    n
    0.19
     =
    0.18
    they
    0.18
    POSITIVE LOGITS
     contexts
    0.43
     terms
    0.39
     spite
    0.38
     relation
    0.37
     regards
    0.35
     realms
    0.35
     lieu
    0.33
     conjunction
    0.32
     accordance
    0.31
     regard
    0.31
    Activations Density 0.270%

    No Known Activations