© 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. 129617
    Prev
    Next
    INDEX
    Explanations

    commands docker manifest version

    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
     low
    -0.06
     $*$
    -0.06
    pril
    -0.06
     đột
    -0.06
    adors
    -0.06
     एजेंसी
    -0.05
    fprintf
    -0.05
     apporte
    -0.05
     తి
    -0.05
     ingenu
    -0.05
    POSITIVE LOGITS
     vantage
    0.06
     因此
    0.06
     presso
    0.06
     Поэтому
    0.06
     acerca
    0.06
     ottenuto
    0.06
     confession
    0.06
    内心
    0.06
    目前的
    0.06
    sequently
    0.06
    Activations Density 0.022%

    No Known Activations