© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130497
    Prev
    Next
    INDEX
    Explanations

    HDAC, biological, optically, spaghetti

    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
     Permanent
    -0.06
    eating
    -0.06
    根据
    -0.06
     возрасте
    -0.06
    ocus
    -0.06
     বিয়ে
    -0.06
     formula
    -0.06
    有了
    -0.06
    బాబు
    -0.05
    永遠
    -0.05
    POSITIVE LOGITS
     awakens
    0.06
     Reve
    0.06
     dredging
    0.06
    唤
    0.06
    cognitive
    0.06
     Insight
    0.06
     Reconciliation
    0.06
    ใบ
    0.06
    foregroundView
    0.06
    ocultural
    0.06
    Activations Density 0.007%

    No Known Activations