© 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. 117438
    Prev
    Next
    INDEX
    Explanations

    {};

    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
    റായി
    -0.06
    Possibly
    -0.06
     possibly
    -0.06
    㳒
    -0.06
    可能是
    -0.06
    6
    -0.05
     algunos
    -0.05
    Possible
    -0.05
    За
    -0.05
    FIC
    -0.05
    POSITIVE LOGITS
     supremely
    0.08
     spectacularly
    0.07
     also
    0.07
     Also
    0.07
     epicenter
    0.07
     exquisitely
    0.06
     pampered
    0.06
    他也
    0.06
    Also
    0.06
     også
    0.06
    Activations Density 0.005%

    No Known Activations