© 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. 116718
    Prev
    Next
    INDEX
    Explanations

    folklore, legends, names, sequences, random

    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
     culminates
    -0.07
     superlative
    -0.06
    featuresMatrix
    -0.06
    AUTHORIZED
    -0.06
    necks
    -0.06
    hältnis
    -0.06
     समास
    -0.06
     diámetro
    -0.06
     culminating
    -0.06
     أو
    -0.06
    POSITIVE LOGITS
    random
    0.06
     patrol
    0.05
     cal
    0.05
    gu
    0.05
    aka
    0.05
    ool
    0.05
    随机
    0.05
     Tucker
    0.05
    represented
    0.05
    apel
    0.05
    Activations Density 0.003%

    No Known Activations