© 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. 7-GEMMASCOPE-2-RES-16K
    7. 1945
    Prev
    Next
    INDEX
    Explanations

    concatenation operation

    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_7_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
    aki
    1.75
    usa
    1.68
    li
    1.65
    ka
    1.48
    na
    1.48
     Der
    1.46
    ’
    1.40
     Bars
    1.40
     Bene
    1.39
     Train
    1.39
    POSITIVE LOGITS
    ֩
    1.78
    [,]
    1.74
     inhe
    1.70
    ერთ
    1.68
     तरी
    1.64
     unsub
    1.63
    GraphQL
    1.60
    ется
    1.60
     बिलकुल
    1.59
    REFERENCE
    1.59
    Activations Density 0.014%

    No Known Activations