© 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. 432
    Prev
    Next
    INDEX
    Explanations

    dice rolls, legal entity, showdown

    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
    يع
    1.05
    الح
    1.01
    л
    0.91
    ол
    0.88
    يت
    0.84
    倆
    0.84
    ע
    0.83
    세
    0.83
    觓
    0.83
    俩
    0.82
    POSITIVE LOGITS
    s
    0.98
    มือ
    0.96
    writes
    0.95
     fabrik
    0.93
    ς
    0.91
    thirsty
    0.91
     дошко
    0.90
     Schreiber
    0.89
    skij
    0.89
    writers
    0.88
    Activations Density 0.000%

    No Known Activations