© 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. 117615
    Prev
    Next
    INDEX
    Explanations

    getting readers or users

    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
     خلال
    -0.06
    ման
    -0.06
     realizada
    -0.06
    ใช้
    -0.06
     defiance
    -0.06
     საშუალ
    -0.06
    şağı
    -0.06
    這種
    -0.05
     সিনেমায়
    -0.05
     சிறிய
    -0.05
    POSITIVE LOGITS
     affair
    0.06
    ্া
    0.06
     образования
    0.06
     क्वे
    0.05
     excellent
    0.05
     Excellent
    0.05
    ("",
    0.05
     Ville
    0.05
     edu
    0.05
     सिर
    0.05
    Activations Density 0.013%

    No Known Activations