© 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-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 1732
    Prev
    Next
    INDEX
    Explanations

    abstract syntax trees

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_22_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     context
    0.60
     married
    0.59
     Context
    0.58
     करीबी
    0.57
    সম্প
    0.57
    🅻
    0.56
     Verbindung
    0.56
    লেট
    0.56
    ান্তর
    0.55
    zys
    0.52
    POSITIVE LOGITS
     Phe
    0.70
    pho
    0.68
    pem
    0.66
     pencil
    0.65
     Ph
    0.64
     Pem
    0.64
    Py
    0.64
    Ph
    0.63
    pager
    0.62
    P
    0.62
    Activations Density 0.493%

    No Known Activations