© 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. 11839
    Prev
    Next
    INDEX
    Explanations

    numbers followed by letters

    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
    7
    0.39
    6
    0.38
    8
    0.37
    5
    0.36
    4
    0.36
     ২২
    0.36
     Nhưng
    0.35
     However
    0.35
     july
    0.34
     Đây
    0.34
    POSITIVE LOGITS
     entwick
    0.34
     conveniences
    0.33
    𝘀
    0.33
    ⊔
    0.33
     வில
    0.31
    𝐥
    0.30
     absolument
    0.29
    以外
    0.29
    თვის
    0.29
    ैश
    0.28
    Activations Density 0.001%

    No Known Activations