© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 119010
    Prev
    Next
    INDEX
    Explanations

    website: https://openfoam

    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
     primarily
    -0.07
    แด
    -0.06
     Primarily
    -0.06
     predominantly
    -0.06
     hauptsächlich
    -0.06
     interfacing
    -0.06
    色的
    -0.06
     лицо
    -0.06
    の中でも
    -0.06
     Mein
    -0.06
    POSITIVE LOGITS
     aqueles
    0.06
    france
    0.05
    Job
    0.05
     nichts
    0.05
     relapse
    0.05
    libr
    0.05
    xen
    0.05
    brit
    0.05
    Makefile
    0.05
    Expires
    0.05
    Activations Density 0.013%

    No Known Activations