© 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. 116825
    Prev
    Next
    INDEX
    Explanations

    Q: ... class

    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
     după
    -0.07
    ாலிக
    -0.07
     iki
    -0.07
    Cantidad
    -0.07
     Autres
    -0.06
     distinct
    -0.06
     वहां
    -0.06
     discreet
    -0.06
    Número
    -0.06
    亞洲
    -0.06
    POSITIVE LOGITS
     L
    0.06
    ci
    0.06
     high
    0.06
    高
    0.05
    বাধিকার
    0.05
     sustained
    0.05
     Pc
    0.05
     c
    0.05
    android
    0.05
    â
    0.05
    Activations Density 0.002%

    No Known Activations