© 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. 120292
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     fyra
    -0.06
    </tbody>
    -0.06
    removeChild
    -0.06
     オン
    -0.06
    ♂
    -0.06
     उन
    -0.06
     pubblico
    -0.06
     Publicity
    -0.06
     như
    -0.05
     вернуться
    -0.05
    POSITIVE LOGITS
     póź
    0.07
     fairly
    0.07
    maybe
    0.06
     dość
    0.06
     دیگه
    0.06
     assez
    0.06
     kés
    0.06
     moderately
    0.06
     theses
    0.06
     subsequent
    0.06
    Activations Density 0.000%

    No Known Activations