© 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. 119533
    Prev
    Next
    INDEX
    Explanations

    AttributeConverter Montell Elucidating

    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
     boosted
    -0.06
     हरकत
    -0.06
     revelations
    -0.06
    女子
    -0.06
    েন্টস
    -0.06
    selectAll
    -0.05
     calls
    -0.05
    trial
    -0.05
    MessageNow
    -0.05
    消息
    -0.05
    POSITIVE LOGITS
     уверен
    0.06
    准确
    0.06
    ัว
    0.06
     remplacement
    0.06
    Make
    0.06
     communities
    0.06
     masyarakat
    0.06
     replacement
    0.06
    understand
    0.06
    laz
    0.06
    Activations Density 0.003%

    No Known Activations