© 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. 129490
    Prev
    Next
    INDEX
    Explanations

    completion, total, finished

    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
     हल्का
    -0.07
    revoke
    -0.06
    вная
    -0.06
     persist
    -0.06
     Maize
    -0.06
     interchanges
    -0.06
     pores
    -0.06
     modes
    -0.06
    "},{"
    -0.06
     retained
    -0.06
    POSITIVE LOGITS
    Кто
    0.06
     Bhi
    0.06
    Each
    0.06
    TARGET
    0.06
     ofrece
    0.06
    erté
    0.06
     सोचा
    0.06
    Œ
    0.06
     Каждый
    0.06
     biotechnology
    0.06
    Activations Density 0.002%

    No Known Activations