© 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. 128765
    Prev
    Next
    INDEX
    Explanations

    density, dpi, virtual, Premium

    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
     sometimes
    -0.06
     súa
    -0.06
    sometimes
    -0.06
     सुरु
    -0.06
    ภาค
    -0.06
    abinieri
    -0.06
    कभी
    -0.06
    अभी
    -0.05
     ஓய்
    -0.05
     standby
    -0.05
    POSITIVE LOGITS
     متجه
    0.07
     intersected
    0.06
     horrendous
    0.06
     बावजूद
    0.06
    墓
    0.06
    chond
    0.06
     nutzt
    0.06
    ctree
    0.06
     affecting
    0.06
     مشابه
    0.06
    Activations Density 0.001%

    No Known Activations