© 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. 119331
    Prev
    Next
    INDEX
    Explanations

    Stephanie R. or official reports

    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
     =
    -0.08
     Because
    -0.07
    Because
    -0.07
     because
    -0.07
    Again
    -0.07
    =
    -0.06
     เพราะ
    -0.06
     the
    -0.06
     Again
    -0.06
     porque
    -0.06
    POSITIVE LOGITS
    fake
    0.07
     reconfiguration
    0.07
    Fake
    0.06
     escrit
    0.06
     moisturizer
    0.06
     çocuklar
    0.06
     fake
    0.06
    𝘽
    0.06
     драй
    0.06
     Disable
    0.06
    Activations Density 0.003%

    No Known Activations