© 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. 133
    Prev
    Next
    INDEX
    Explanations

    project/product names offering something

    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
    perturb
    0.47
     вообще
    0.47
     বিপর্য
    0.46
    那边
    0.45
    _{*}\
    0.44
    if
    0.44
    FieldError
    0.44
     riesgos
    0.43
     думать
    0.42
    🤮
    0.42
    POSITIVE LOGITS
     biedt
    0.88
     provides
    0.82
     serves
    0.80
     предлагает
    0.80
     embodies
    0.79
     menawarkan
    0.79
    是一個
    0.79
     offers
    0.78
     exemplifies
    0.78
     empowers
    0.77
    Activations Density 0.075%

    No Known Activations