© 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. 120734
    Prev
    Next
    INDEX
    Explanations

    should followed by verb

    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
     their
    -0.06
     there
    -0.06
     उनके
    -0.06
     eine
    -0.06
     metaphorical
    -0.06
    ใน
    -0.06
    !
    -0.06
    Except
    -0.06
     loro
    -0.05
    POSITIVE LOGITS
     करणाऱ्या
    0.07
    rather
    0.07
    prefer
    0.06
    insta
    0.06
     raczej
    0.06
     thinks
    0.06
     rather
    0.06
    দেখে
    0.06
    biggest
    0.06
     nossos
    0.06
    Activations Density 0.026%

    No Known Activations