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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8608
    Prev
    Next
    INDEX
    Explanations

    physical actions and relax states

    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_34/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
     mengatasi
    -0.85
     kepentingan
    -0.84
     pengaruh
    -0.82
    掴
    -0.82
     gestos
    -0.81
     memutus
    -0.81
     valores
    -0.78
     tersebut
    -0.77
     sulit
    -0.77
     penurunan
    -0.77
    POSITIVE LOGITS
     keep
    1.17
     keeping
    1.17
    keeping
    1.13
     relax
    1.13
     raise
    1.09
     focus
    1.08
     slowly
    1.05
    Keeping
    1.05
     relaxed
    1.05
     imagine
    1.04
    Activations Density 0.015%

    No Known Activations