© 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. 128497
    Prev
    Next
    INDEX
    Explanations

    kind of

    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
    HOW
    -0.06
    看待
    -0.06
     რამდენ
    -0.06
    所谓的
    -0.06
     Bereits
    -0.06
     minul
    -0.06
    ையைப்
    -0.06
    aites
    -0.05
     उत्सा
    -0.05
    今天
    -0.05
    POSITIVE LOGITS
     multiplied
    0.07
     jika
    0.06
    如果
    0.06
    乘以
    0.06
     these
    0.06
     अनुसार
    0.06
     multiplier
    0.06
     ஆரோக்கிய
    0.05
     তুমি
    0.05
     如果
    0.05
    Activations Density 0.011%

    No Known Activations