© 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. 128265
    Prev
    Next
    INDEX
    Explanations

    written to, developing capabilities

    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
    你
    -0.07
    里的
    -0.07
    これからも
    -0.06
     Your
    -0.06
     여러분
    -0.06
     Kosovo
    -0.06
     your
    -0.06
                                   
    -0.06
     estaremos
    -0.06
     உங்க
    -0.06
    POSITIVE LOGITS
     littered
    0.07
     बेहद
    0.06
     some
    0.06
     almeno
    0.06
     alcuni
    0.06
     déchir
    0.06
     spinster
    0.06
    ?),
    0.06
     algumas
    0.06
     strikingly
    0.06
    Activations Density 0.035%

    No Known Activations