© 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. 117263
    Prev
    Next
    INDEX
    Explanations

    script or code blocks

    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
     Ayn
    -0.06
     multitude
    -0.06
     proofs
    -0.06
     그렇지
    -0.06
     machinery
    -0.06
    )),
    -0.06
    мно
    -0.06
     journey
    -0.06
    old
    -0.05
     detected
    -0.05
    POSITIVE LOGITS
    超市
    0.06
    rö
    0.06
     INEC
    0.06
     இரண்ட
    0.06
     ultimately
    0.06
     Ultimately
    0.06
     یا
    0.06
     গম
    0.05
     या
    0.05
     Ō
    0.05
    Activations Density 0.001%

    No Known Activations