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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 129822
    Prev
    Next
    INDEX
    Explanations

    verbs followed by in, by, or with

    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
    全然
    -0.96
     Gottesdienst
    -0.90
    |}\
    -0.88
     jenes
    -0.86
    rceil
    -0.86
     segala
    -0.85
     direção
    -0.84
    ualitas
    -0.84
     दे
    -0.84
    ༤
    -0.84
    POSITIVE LOGITS
    
    1.04
    ឋ
    1.00
    krishna
    0.98
    最初に
    0.97
     this
    0.96
    辦法
    0.95
    sekten
    0.95
    téri
    0.94
    💩
    0.94
    āk
    0.92
    Activations Density 0.071%

    No Known Activations