© 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. 118458
    Prev
    Next
    INDEX
    Explanations

    parentheses or brackets

    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
     a
    -0.06
     porcelain
    -0.06
     chois
    -0.06
    楂
    -0.06
    vì
    -0.06
     পদ্
    -0.06
     idha
    -0.06
     nieuwe
    -0.06
    主張
    -0.06
     പോലുള്ള
    -0.06
    POSITIVE LOGITS
     oftentimes
    0.06
     literalmente
    0.06
     методи
    0.06
     resources
    0.06
    所需
    0.05
     DIRECTIONS
    0.05
    ometimes
    0.05
    லி
    0.05
     reimb
    0.05
    lendir
    0.05
    Activations Density 0.008%

    No Known Activations