© 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. 117461
    Prev
    Next
    INDEX
    Explanations

    anonymous guest Untitled

    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
    ⲟ
    -0.06
     জার্মান
    -0.06
    नवीन
    -0.06
     fowl
    -0.06
    他们在
    -0.06
    Final
    -0.05
     sickening
    -0.05
     kelet
    -0.05
     (*
    -0.05
     mereka
    -0.05
    POSITIVE LOGITS
     дода
    0.06
    Specified
    0.06
     most
    0.06
     Generic
    0.06
     полови
    0.06
     overtake
    0.06
     for
    0.06
     ಎರಡ
    0.06
     одну
    0.06
     added
    0.06
    Activations Density 0.002%

    No Known Activations