© 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. 116407
    Prev
    Next
    INDEX
    Explanations

    configuration options

    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
    ]
    -0.06
    \}
    -0.06
                             
    -0.06
    ㅣ
    -0.06
     lg
    -0.05
     incrementally
    -0.05
    確實
    -0.05
    integer
    -0.05
     المدر
    -0.05
     amelior
    -0.05
    POSITIVE LOGITS
    Despite
    0.07
     Как
    0.07
    ಸ್ಟ್
    0.07
    nW
    0.07
     несмотря
    0.07
    STO
    0.07
    До
    0.06
     bouch
    0.06
    abord
    0.06
     aufgrund
    0.06
    Activations Density 0.015%

    No Known Activations