© 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. 117246
    Prev
    Next
    INDEX
    Explanations

    atypia, dysplasia, necrosis, ballooning

    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
     anche
    -0.07
     समोर
    -0.07
     trinity
    -0.07
     cercando
    -0.06
    ByType
    -0.06
     nhạc
    -0.06
     även
    -0.06
    शेष
    -0.06
     представлена
    -0.06
     representando
    -0.06
    POSITIVE LOGITS
    要
    0.06
    ++++++++
    0.06
    editText
    0.06
    श्न
    0.06
    RULES
    0.06
     aturan
    0.05
    迸
    0.05
     fren
    0.05
    ảy
    0.05
     Purch
    0.05
    Activations Density 0.001%

    No Known Activations