© 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. 117695
    Prev
    Next
    INDEX
    Explanations

    line or row context

    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
     Teaching
    -0.06
    toj
    -0.06
    Teaching
    -0.06
    लेक्ट
    -0.05
     ದೇ
    -0.05
     Fracture
    -0.05
    ormal
    -0.05
     хотя
    -0.05
     maxLength
    -0.05
     konkret
    -0.05
    POSITIVE LOGITS
    Maritime
    0.07
     actions
    0.07
     hulle
    0.06
    蛩
    0.06
     nutritive
    0.06
     Maritime
    0.06
     idade
    0.06
    actions
    0.06
     emulsions
    0.06
     لگانا
    0.05
    Activations Density 0.001%

    No Known Activations