© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 57
    Prev
    Next
    INDEX
    Explanations

    beginning God said

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_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
    -
    0.92
     (
    0.78
      
    0.78
    ,
    0.71
     and
    0.71
    -,
    0.70
    :
    0.70
    class
    0.68
     -
    0.67
     e
    0.66
    POSITIVE LOGITS
     incroyable
    1.21
     delicioso
    1.15
     lleno
    1.14
     unglaublich
    1.11
     electricidad
    1.10
     incrível
    1.09
    ুতরাং
    1.09
     returnPacket
    1.09
     tranquila
    1.08
     énorme
    1.07
    Activations Density 0.726%

    No Known Activations