© 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. 116046
    Prev
    Next
    INDEX
    Explanations

    `E-Filing` or `association`

    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
     continual
    -0.07
     budgeting
    -0.06
     showed
    -0.06
     خطوات
    -0.06
     continu
    -0.06
     continuously
    -0.06
     betrayed
    -0.06
    ிகளும்
    -0.06
     ſ
    -0.06
     eagerness
    -0.06
    POSITIVE LOGITS
     سونے
    0.06
    ☦
    0.06
     නම්
    0.06
    Méd
    0.06
     нескольких
    0.06
     Rhodes
    0.06
     лично
    0.06
     único
    0.06
    もの
    0.06
    確
    0.05
    Activations Density 0.001%

    No Known Activations