© 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-3-270M
    5. 12-GEMMASCOPE-2-RES-16K
    7. 5301
    Prev
    Next
    INDEX
    Explanations

    counterpart, equivalent, successor, related

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_12_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
    udence
    1.71
    йма
    1.71
    ology
    1.67
     clínica
    1.66
    ecia
    1.64
    恚
    1.63
     وه
    1.63
    宀
    1.62
    щений
    1.62
    wire
    1.60
    POSITIVE LOGITS
     counterpart
    2.63
     counterparts
    2.63
     successors
    2.60
     successor
    2.54
     competitor
    2.45
     rivals
    2.42
     analogues
    2.41
     equivalents
    2.38
     predecess
    2.33
     rival
    2.29
    Activations Density 0.471%

    No Known Activations