© 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. 46
    Prev
    Next
    INDEX
    Explanations

    to be or have

    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
     а
    0.85
     a
    0.68
    AL
    0.68
    あ
    0.67
     the
    0.64
    이랑
    0.64
     மற்றும்
    0.63
    बल
    0.62
    о
    0.62
     알
    0.62
    POSITIVE LOGITS
     aberrations
    0.66
    ¹
    0.64
     etched
    0.63
     tincture
    0.63
     realizzato
    0.61
     ermöglichen
    0.60
     indel
    0.59
    sächlich
    0.59
    ,’
    0.59
     विस्तार
    0.59
    Activations Density 0.861%

    No Known Activations