© 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. 120671
    Prev
    Next
    INDEX
    Explanations

    related to

    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
     constitutes
    -0.06
     constituting
    -0.06
     indicates
    -0.06
     underlies
    -0.06
     sha
    -0.06
    avourable
    -0.05
    Tib
    -0.05
     falls
    -0.05
     clarifies
    -0.05
     reminis
    -0.05
    POSITIVE LOGITS
     появ
    0.07
     with
    0.07
     y
    0.07
    乜
    0.06
     अवस्थ
    0.06
     BAFTA
    0.06
     रखते
    0.06
    最短
    0.06
    表现
    0.06
     из
    0.06
    Activations Density 0.012%

    No Known Activations