© 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. 14093
    Prev
    Next
    INDEX
    Explanations

    information, section, commentary, nonexistent, steps, pm

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     scallops
    0.80
     allong
    0.80
    ຈ
    0.80
    スン
    0.79
    oporosis
    0.77
     occuper
    0.77
    线性
    0.77
    法則
    0.77
     omission
    0.76
     creditors
    0.75
    POSITIVE LOGITS
    ي
    0.85
     און
    0.75
    ulty
    0.75
     эксперти
    0.75
    zeuge
    0.75
    י
    0.72
    un
    0.72
    examtype
    0.71
     Chesterfield
    0.71
    chen
    0.70
    Activations Density 0.000%

    No Known Activations