© 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. 28
    Prev
    Next
    INDEX
    Explanations

    will/would followed by verb

    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
    нің
    1.02
    тся
    0.97
    нача
    0.94
    ।
    0.93
     hues
    0.90
    ның
    0.89
     частиц
    0.89
    му
    0.88
     eradic
    0.85
    щихся
    0.84
    POSITIVE LOGITS
    oughby
    1.11
    ก
    1.05
    hite
    1.04
    ic
    1.02
    ל
    0.99
    یر
    0.96
    enek
    0.91
    gallon
    0.89
    ต้อง
    0.89
    าค
    0.88
    Activations Density 6.839%

    No Known Activations