© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 10602
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_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
    NAMES
    0.82
    য
    0.82
    و
    0.81
    Names
    0.80
    様々な
    0.80
     делать
    0.77
    }}=-
    0.77
    DEFIN
    0.76
    যা
    0.75
    สุขภาพ
    0.74
    POSITIVE LOGITS
    washed
    0.82
    nosed
    0.74
    bidden
    0.69
    scaled
    0.68
    岁的
    0.68
    蝉
    0.68
    也会
    0.68
    board
    0.65
    colored
    0.65
    iscono
    0.65
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.