© 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. 120150
    Prev
    Next
    INDEX
    Explanations

    inserting data into structures

    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
     assez
    -0.07
     это
    -0.06
     zwei
    -0.06
     लि
    -0.06
     drei
    -0.06
     implicated
    -0.06
     axiomatic
    -0.06
     বিশেষ
    -0.06
    वर्तमान
    -0.06
     این
    -0.06
    POSITIVE LOGITS
     a
    0.08
     शेड्यूल
    0.06
    カ
    0.05
     -*-
    0.05
    所述
    0.05
     statement
    0.05
     Replies
    0.05
     odp
    0.05
     description
    0.05
    ަތ
    0.05
    Activations Density 0.027%

    No Known Activations