© 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. 120116
    Prev
    Next
    INDEX
    Explanations

    directly copy structure or bits

    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
     intrac
    -0.06
     बृह
    -0.06
     Ultimate
    -0.06
     Regeln
    -0.06
     ultimate
    -0.06
     이전
    -0.06
     thuộc
    -0.06
    se
    -0.06
     teaming
    -0.06
    所属
    -0.06
    POSITIVE LOGITS
     unaltered
    0.08
     그대로
    0.08
     raw
    0.08
    そのまま
    0.08
     unchanged
    0.08
     our
    0.07
     unmodified
    0.07
     unprocessed
    0.07
     unsere
    0.07
     naš
    0.06
    Activations Density 0.049%

    No Known Activations