© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 118665
    Prev
    Next
    INDEX
    Explanations

    father's name

    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
    ,
    -0.07
    List
    -0.06
    ],
    -0.06
     arty
    -0.05
    から
    -0.05
    oles
    -0.05
    Mac
    -0.05
    ));
    -0.05
    :
    -0.05
    Pa
    -0.05
    POSITIVE LOGITS
     какую
    0.07
    ALTERNATIVNAMEN
    0.06
     anteriormente
    0.06
     numero
    0.06
     ранее
    0.06
     inappropriate
    0.06
    मस्कार
    0.06
     jumpa
    0.06
     acteur
    0.06
     данной
    0.06
    Activations Density 0.011%

    No Known Activations