© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 9411
    Prev
    Next
    INDEX
    Explanations

    version numbers and releases

    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
     outcome
    0.86
     উহা
    0.83
    િવસ
    0.83
     reversal
    0.82
     ಬಿಯ
    0.81
     使っ
    0.81
     repellent
    0.80
     술
    0.80
     cracker
    0.79
    芋
    0.79
    POSITIVE LOGITS
    _
    0.72
    enar
    0.70
    a
    0.67
    ت
    0.67
    T
    0.64
    nodes
    0.60
     ==
    0.59
    null
    0.59
    ._
    0.58
    净
    0.57
    Activations Density 0.076%

    No Known Activations