© 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
    2. Gemma-3-4B-IT
    3. 22-GEMMASCOPE-2-RES-16K
    4. 7547
    Prev
    Next
    INDEX
    Explanations

    abstract concepts and constructions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-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
     খ্যা
    0.68
     واست
    0.68
     MJ
    0.67
     Mister
    0.65
    <unused527>
    0.65
     Sve
    0.65
    <unused320>
    0.64
     hugely
    0.64
     أش
    0.64
    $.}
    0.63
    POSITIVE LOGITS
     belladone
    0.72
    ม่
    0.69
    য়ে
    0.67
     écoles
    0.65
    सीन
    0.64
     salario
    0.64
    isen
    0.64
    ंक
    0.62
    Ï
    0.61
    មូល
    0.61
    Activations Density 1.763%

    No Known Activations