© 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. 117016
    Prev
    Next
    INDEX
    Explanations

    antibody, transient, controllers, drive

    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
     RETURNS
    -0.07
     returns
    -0.07
    のですが
    -0.06
    returns
    -0.06
     PRIMARY
    -0.06
    tragung
    -0.06
    日本の
    -0.06
    舩
    -0.06
     মনোর
    -0.06
     vacancy
    -0.06
    POSITIVE LOGITS
    ?’”
    0.06
     senza
    0.06
     luôn
    0.06
    青山
    0.05
     actif
    0.05
     earl
    0.05
     interrogate
    0.05
     tanpa
    0.05
     tự
    0.05
    Instr
    0.05
    Activations Density 0.116%

    No Known Activations