© 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. 119844
    Prev
    Next
    INDEX
    Explanations

    complete with

    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
     week
    -0.07
     сильнее
    -0.07
    idays
    -0.07
     zeigen
    -0.07
     día
    -0.06
     diurnal
    -0.06
     jeudi
    -0.06
     thursday
    -0.06
     Thursday
    -0.06
     هفته
    -0.06
    POSITIVE LOGITS
     Priorities
    0.06
     inhaled
    0.06
    ...\...\...\...\
    0.06
     digesting
    0.06
     pleasant
    0.06
     value
    0.06
    ູນ
    0.06
    子
    0.06
    jr
    0.06
    φ
    0.06
    Activations Density 0.015%

    No Known Activations