© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 120781
    Prev
    Next
    INDEX
    Explanations

    space launch components

    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
     Operation
    -0.08
    operation
    -0.07
     operation
    -0.07
    ieurs
    -0.06
     운영
    -0.06
    Operation
    -0.06
     projects
    -0.06
    ปริ
    -0.06
     Develop
    -0.06
    masing
    -0.06
    POSITIVE LOGITS
     čtyř
    0.07
    というのは
    0.07
     Minuten
    0.06
     gmin
    0.06
    乡村
    0.06
    checked
    0.06
     sluggish
    0.06
     энерги
    0.06
    tailed
    0.06
     привы
    0.06
    Activations Density 0.006%

    No Known Activations