© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 117793
    Prev
    Next
    INDEX
    Explanations

    class declaration constructors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/gemma-4-saes/gemma-4-31b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     다른
    -0.07
     choć
    -0.07
     अन्य
    -0.07
     потом
    -0.07
     but
    -0.07
     срав
    -0.07
    했지만
    -0.06
     další
    -0.06
     хотя
    -0.06
     although
    -0.06
    POSITIVE LOGITS
    !..
    0.07
    !...
    0.06
     ORGAN
    0.06
    如果在
    0.06
    !"
    0.06
    !
    0.06
     Organ
    0.06
     (&
    0.05
     可以
    0.05
    Organ
    0.05
    Activations Density 0.001%

    No Known Activations