© 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. 128080
    Prev
    Next
    INDEX
    Explanations

    email headers and footers

    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
    Negative Logits
    ;
    -0.07
     diesen
    -0.07
     Wenn
    -0.06
     ২৮
    -0.06
    т
    -0.06
     این
    -0.06
     einst
    -0.06
    యత్
    -0.06
    Achievements
    -0.06
    geschossiges
    -0.06
    POSITIVE LOGITS
     
    0.06
    Track
    0.06
    richten
    0.05
    DC
    0.05
    dX
    0.05
     offset
    0.05
     நானும்
    0.05
    HintPath
    0.05
     éventuellement
    0.05
     الواحد
    0.05
    Activations Density 0.002%

    No Known Activations