© 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. 242
    Prev
    Next
    INDEX
    Explanations

    programming library keywords

    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
    in
    1.69
    og
    1.25
    on
    1.19
    a
    1.13
    this
    1.06
    ie
    1.04
    ish
    1.02
    est
    1.00
    iz
    1.00
    for
    0.97
    POSITIVE LOGITS
     möj
    1.26
     décrites
    1.17
     fornisce
    1.14
    你
    1.09
    ון
    1.07
     έχει
    1.07
     menciona
    1.06
     vært
    1.05
     indicado
    1.03
     zapewnia
    1.03
    Activations Density 0.040%

    No Known Activations