© 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. 119509
    Prev
    Next
    INDEX
    Explanations

    numbers followed by tokens

    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
    <0xE3>
    -0.06
    숍
    -0.05
    ;
    -0.05
    Sub
    -0.05
     që
    -0.05
    வுடன்
    -0.05
     své
    -0.05
     שלא
    -0.05
    CHRIST
    -0.05
    POSITIVE LOGITS
     a
    0.07
     crores
    0.07
     an
    0.07
     existence
    0.07
     मागणी
    0.07
     has
    0.07
    姑娘
    0.06
     creates
    0.06
     باید
    0.06
     values
    0.06
    Activations Density 0.001%

    No Known Activations