Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 12019
    Prev
    Next
    INDEX
    Explanations

    phrases using prepositions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     getragen
    -1.09
     necesariamente
    -1.05
    بيل
    -1.04
    gı
    -1.03
     gwaran
    -1.03
     gewohnt
    -1.03
     estudian
    -1.01
     I
    -1.00
     langsam
    -0.99
     لكل
    -0.99
    POSITIVE LOGITS
     this
    1.27
    instead
    1.03
    Consul
    1.00
    視点
    0.99
     יכול
    0.99
     encuentre
    0.98
     воспользоваться
    0.97
     instead
    0.94
    从此
    0.94
     legislat
    0.93
    Activations Density 0.062%

    No Known Activations