© 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. 95
    Prev
    Next
    INDEX
    Explanations

    specific entities and proper nouns

    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
    ice
    0.79
    ó
    0.75
    不是
    0.74
    cek
    0.74
    mut
    0.71
    ite
    0.71
    iter
    0.70
    aa
    0.69
    ا
    0.69
    कर
    0.68
    POSITIVE LOGITS
     filosóf
    1.15
     âng
    1.09
     sitios
    1.08
     pitfalls
    1.07
     ändern
    1.06
     Wechsler
    1.05
     Wszyst
    1.05
     aumenta
    1.04
     selber
    1.04
     Honestly
    1.03
    Activations Density 0.000%

    No Known Activations