© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 33329
    Prev
    Next
    INDEX
    Explanations

    object or action ending a clause

    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
     to
    -1.87
    事で
    -1.11
    為に
    -1.02
    ことで
    -0.99
     उन्हें
    -0.98
    因为它
    -0.90
    讼
    -0.88
     они
    -0.87
     theyre
    -0.87
    還好
    -0.87
    POSITIVE LOGITS
     ולה
    1.12
     방법
    1.08
     about
    1.08
     such
    0.96
     from
    0.94
    IfNeeded
    0.93
    anwal
    0.93
    målet
    0.90
    ✨
    0.90
    ieve
    0.88
    Activations Density 0.115%

    No Known Activations