© 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
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 10193
    Prev
    Next
    INDEX
    Explanations

    offering alternative prompts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_22_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ",
    0.83
     meaning
    0.82
    orsche
    0.81
     AliExpress
    0.81
     Meaning
    0.81
    :{
    0.81
    oczes
    0.80
    rası
    0.80
    roni
    0.79
     lekker
    0.78
    POSITIVE LOGITS
     শির
    0.93
    
    0.92
     나무
    0.91
    
    0.91
    akukannya
    0.88
     thảo
    0.88
    
    0.87
    Spectrum
    0.86
    RDF
    0.86
     глоба
    0.85
    Activations Density 0.005%

    No Known Activations