© 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. 128387
    Prev
    Next
    INDEX
    Explanations

    conjunctions leading to actions

    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
     which
    -0.08
     जोकि
    -0.07
     ktore
    -0.06
     वाह
    -0.06
     kaik
    -0.06
    wow
    -0.06
     של
    -0.06
     a
    -0.06
    cial
    -0.06
     robi
    -0.06
    POSITIVE LOGITS
     also
    0.06
    cko
    0.06
     supple
    0.06
     também
    0.06
     parameters
    0.06
    ಲ್ಲೂ
    0.06
     ？
    0.06
     Parameters
    0.05
     Legislature
    0.05
    を中心に
    0.05
    Activations Density 0.018%

    No Known Activations