© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 119004
    Prev
    Next
    INDEX
    Explanations

    notice of intent

    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
    inkt
    -0.87
    arim
    -0.86
    Ideal
    -0.84
    żdż
    -0.81
    iasaan
    -0.81
    あれ
    -0.80
    Président
    -0.80
    兴奋
    -0.80
    応募
    -0.78
     cascading
    -0.78
    POSITIVE LOGITS
     intention
    1.91
     intent
    1.52
     intended
    1.23
     Intent
    1.20
     intentions
    1.15
     Intention
    1.09
     change
    1.08
     impending
    1.06
     intend
    1.00
    intention
    0.96
    Activations Density 0.031%

    No Known Activations