© 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. 16292
    Prev
    Next
    INDEX
    Explanations

    examples of lists or explanations

    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
     뛰어
    0.71
    ру
    0.66
    пример
    0.65
    нды
    0.65
    ა
    0.64
     그냥
    0.63
     資
    0.63
     간단
    0.63
     바람
    0.63
    ндо
    0.63
    POSITIVE LOGITS
     and
    0.81
     (“
    0.70
     or
    0.70
     (‘
    0.63
     và
    0.60
    人和
    0.60
     மற்றும்
    0.59
    或
    0.57
    和
    0.57
    者的
    0.56
    Activations Density 0.198%

    No Known Activations