© 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. 128902
    Prev
    Next
    INDEX
    Explanations

    is also

    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
     any
    -0.06
    !
    -0.06
     To
    -0.06
     Alors
    -0.06
     Any
    -0.06
    :
    -0.06
    -
    -0.05
    any
    -0.05
     경우에는
    -0.05
     belieb
    -0.05
    POSITIVE LOGITS
     этих
    0.08
     estos
    0.08
     цих
    0.07
     pollute
    0.07
     těchto
    0.07
    這些
    0.07
    నుంది
    0.06
    Estos
    0.06
    这些
    0.06
     polluted
    0.06
    Activations Density 0.003%

    No Known Activations