© 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. 117628
    Prev
    Next
    INDEX
    Explanations

    illegal content distribution

    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
     horrible
    -0.07
     interactive
    -0.06
     superb
    -0.06
     horribly
    -0.06
     fantastic
    -0.06
     papillary
    -0.06
     oznac
    -0.06
    🎆
    -0.06
     inquest
    -0.06
    jh
    -0.06
    POSITIVE LOGITS
     of
    0.06
     copying
    0.06
    竊
    0.06
    protos
    0.06
     पॉपुलर
    0.06
    ഹ
    0.06
    涮
    0.06
     manera
    0.06
     одного
    0.06
     kesel
    0.06
    Activations Density 0.004%

    No Known Activations