© 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. 119708
    Prev
    Next
    INDEX
    Explanations

    `row` followed by attributes or identifiers

    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
    稳
    -0.06
    种类
    -0.06
     депозиттик
    -0.06
    ↵↵↵
    -0.06
    )}^{\
    -0.06
    ↵↵↵↵↵↵
    -0.06
    সর্ব
    -0.06
    FAC
    -0.06
    -}\
    -0.06
     eigenstates
    -0.06
    POSITIVE LOGITS
     cuyo
    0.07
    До
    0.06
    fit
    0.06
    𝙱
    0.06
    ?,
    0.06
    roep
    0.06
     Bl
    0.06
     gdzie
    0.06
     particularly
    0.05
     ekstra
    0.05
    Activations Density 0.109%

    No Known Activations