© 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. 128318
    Prev
    Next
    INDEX
    Explanations

    command line usage and syntax

    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
     нашу
    -0.07
     lenses
    -0.06
     फाइबर
    -0.06
     అనుమ
    -0.06
    SCHEMA
    -0.06
     commentary
    -0.06
    ुरा
    -0.06
     senza
    -0.06
    Diameter
    -0.06
    hurst
    -0.06
    POSITIVE LOGITS
     ১
    0.06
     अभिषेक
    0.05
     inclement
    0.05
     depending
    0.05
     ers
    0.05
     tiết
    0.05
    I
    0.05
     با
    0.05
     decre
    0.05
    okes
    0.05
    Activations Density 0.008%

    No Known Activations