© 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. 116701
    Prev
    Next
    INDEX
    Explanations

    code identifiers like id and primarykey

    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
     আরেক
    -0.07
    вших
    -0.06
     vždy
    -0.06
    包括
    -0.06
     successors
    -0.06
    下的
    -0.06
    嘲
    -0.06
     rövid
    -0.06
    无法
    -0.06
    都是
    -0.05
    POSITIVE LOGITS
    ====
    0.06
     fourteen
    0.06
     sixteen
    0.06
    netz
    0.06
     otto
    0.06
     it
    0.06
     recently
    0.05
     twenty
    0.05
     twelve
    0.05
    :=
    0.05
    Activations Density 0.001%

    No Known Activations