© 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. 120433
    Prev
    Next
    INDEX
    Explanations

    section headers or titles

    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
    .
    -0.07
    ,
    -0.06
    already
    -0.05
     değerli
    -0.05
    either
    -0.05
    i
    -0.05
     그다음에
    -0.05
    whether
    -0.05
     natomiast
    -0.05
     loved
    -0.05
    POSITIVE LOGITS
     снова
    0.08
     możesz
    0.06
     hitam
    0.06
     нередко
    0.06
     अराउंड
    0.06
     لئے
    0.06
    あなたの
    0.06
    𢎞
    0.06
     мень
    0.06
     spesso
    0.06
    Activations Density 0.001%

    No Known Activations