© 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. 128386
    Prev
    Next
    INDEX
    Explanations

    names and policies

    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
     waiters
    -0.07
    тері
    -0.06
     strikers
    -0.06
     Boyce
    -0.06
     stairway
    -0.06
    edged
    -0.06
     ശരീര
    -0.05
     seem
    -0.05
     fetching
    -0.05
    Qualification
    -0.05
    POSITIVE LOGITS
     બાળક
    0.06
     tetap
    0.06
    设计
    0.06
    精心
    0.06
    最后
    0.06
    にする
    0.06
     Nederland
    0.06
     egyéb
    0.06
    arsch
    0.06
    支持
    0.06
    Activations Density 0.002%

    No Known Activations