© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 128618
    Prev
    Next
    INDEX
    Explanations

    items forming or included in a set

    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
    剩余
    -0.07
    剩下的
    -0.07
    Those
    -0.07
    those
    -0.06
     மூன்றாவது
    -0.06
     Those
    -0.06
     inhomogeneities
    -0.06
    Meh
    -0.06
    bė
    -0.06
    thus
    -0.06
    POSITIVE LOGITS
     donde
    0.08
     که
    0.07
     где
    0.07
     όπου
    0.07
     যেটা
    0.06
     includes
    0.06
     Surety
    0.06
     потому
    0.06
     یک
    0.06
     where
    0.06
    Activations Density 0.061%

    No Known Activations