© 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-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 9373
    Prev
    Next
    INDEX
    Explanations

    processing questions

    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
    Border
    0.92
     Border
    0.87
    coin
    0.83
     border
    0.83
    ocr
    0.82
    觴
    0.81
     obstructive
    0.81
    cong
    0.79
    Sunflower
    0.79
    loot
    0.79
    POSITIVE LOGITS
    liques
    0.87
     közé
    0.85
    bygg
    0.85
     legy
    0.84
    ache
    0.83
    越
    0.80
    amera
    0.78
    #:
    0.77
    সিং
    0.74
    lique
    0.74
    Activations Density 0.054%

    No Known Activations