© 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. 12-GEMMASCOPE-2-RES-16K
    7. 513
    Prev
    Next
    INDEX
    Explanations

    network management

    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_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
    г
    1.14
    к
    1.05
    ير
    0.97
     звезды
    0.96
    versed
    0.93
    ীদার
    0.90
    حد
    0.89
    ਹ
    0.88
    м
    0.87
     fright
    0.86
    POSITIVE LOGITS
    leri
    1.12
    lerini
    1.05
    ttp
    1.04
    dok
    0.94
    的过程中
    0.94
     CTCF
    0.94
    lerin
    0.93
     FLAT
    0.93
    ssa
    0.93
    ların
    0.91
    Activations Density 0.000%

    No Known Activations