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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 17028
    Prev
    Next
    INDEX
    Explanations

    phrases with prepositions

    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_31_width_65k_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
    ised
    0.50
    isn
    0.44
     و
    0.42
    riott
    0.41
    elty
    0.40
    and
    0.39
    ężczy
    0.39
    اب
    0.39
    цију
    0.38
     transpiration
    0.38
    POSITIVE LOGITS
     kilometers
    0.54
    ສາມາດ
    0.53
     Obrigado
    0.52
    ⬤
    0.52
     kilometer
    0.50
    さまざまな
    0.50
     Veja
    0.50
    偷偷
    0.49
     কিলোমিটার
    0.49
     hectares
    0.48
    Activations Density 0.012%

    No Known Activations