© 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. 117081
    Prev
    Next
    INDEX
    Explanations

    rubber masterpiece, shortening, create, gently

    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
     инстру
    -0.06
     जयंती
    -0.06
    ᵀ
    -0.06
    Exclusive
    -0.06
     самый
    -0.06
     तुझे
    -0.06
     beide
    -0.06
     തൊഴിലാ
    -0.06
     mới
    -0.06
     refin
    -0.06
    POSITIVE LOGITS
     अॅ
    0.07
     safely
    0.06
    casus
    0.06
     transmitters
    0.06
     बताओ
    0.06
     wonderful
    0.06
    素晴らしい
    0.06
     [/
    0.05
     Playground
    0.05
    spieler
    0.05
    Activations Density 0.009%

    No Known Activations