© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 117234
    Prev
    Next
    INDEX
    Explanations

    news reports and lists

    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
     csak
    -0.08
     тільки
    -0.08
     tylko
    -0.08
     רק
    -0.07
     only
    -0.07
     solamente
    -0.07
     sólo
    -0.07
     sadece
    -0.06
    襖
    -0.06
    நல்ல
    -0.06
    POSITIVE LOGITS
    From
    0.06
     clues
    0.06
     gj
    0.06
     unemployed
    0.06
     from
    0.05
     parametr
    0.05
     NLR
    0.05
     oldest
    0.05
     yesterday
    0.05
     erforderlich
    0.05
    Activations Density 0.054%

    No Known Activations