© 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. 116730
    Prev
    Next
    INDEX
    Explanations

    code delimiters and names

    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
     ভেঙ্গে
    -0.06
     marad
    -0.06
     leftovers
    -0.06
    geometric
    -0.06
     sebagian
    -0.06
     Så
    -0.06
    WaitFor
    -0.06
    commercial
    -0.06
    んじゃない
    -0.06
     as
    -0.06
    POSITIVE LOGITS
     गौरतलब
    0.06
    相比
    0.06
     보다
    0.06
     time
    0.06
     Austausch
    0.05
     बचपन
    0.05
     undeniably
    0.05
     junto
    0.05
     Karg
    0.05
     accanto
    0.05
    Activations Density 0.001%

    No Known Activations