© 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. 129389
    Prev
    Next
    INDEX
    Explanations

    Clint Eastwood

    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
     তোর
    -0.07
     last
    -0.07
    avat
    -0.07
     diversos
    -0.06
     diversa
    -0.06
     banyaknya
    -0.06
     తనకు
    -0.06
     hará
    -0.06
     använda
    -0.06
    用
    -0.06
    POSITIVE LOGITS
    0
    0.06
     উভয়
    0.06
     の
    0.05
     )
    0.05
     अवधारणा
    0.05
    ibid
    0.05
     आरोग्य
    0.05
     будущее
    0.05
     również
    0.05
     DIV
    0.05
    Activations Density 0.001%

    No Known Activations