© 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. 117227
    Prev
    Next
    INDEX
    Explanations

    written permission

    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
     असल्यास
    -0.08
     "
    -0.06
    gll
    -0.06
     such
    -0.06
     иногда
    -0.06
     clerical
    -0.06
     boasted
    -0.06
    så
    -0.06
     genuinely
    -0.05
     socially
    -0.05
    POSITIVE LOGITS
     تنها
    0.07
     BEFORE
    0.07
     Before
    0.07
    這個
    0.07
    この
    0.07
     ONLY
    0.07
     agonizing
    0.07
     intenso
    0.06
     этой
    0.06
     only
    0.06
    Activations Density 0.001%

    No Known Activations