© 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. 116473
    Prev
    Next
    INDEX
    Explanations

    beginning of sentence

    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
     one
    -0.07
     a
    -0.07
     the
    -0.07
     their
    -0.07
     our
    -0.07
    বর্তমানে
    -0.06
     at
    -0.06
    自身的
    -0.06
    ..?
    -0.06
     benef
    -0.06
    POSITIVE LOGITS
     answers
    0.06
    最初に
    0.06
     시작하겠습니다
    0.06
     iniziare
    0.06
     beginning
    0.06
     voordat
    0.06
     dizziness
    0.06
     komunitas
    0.06
    任何
    0.06
     start
    0.06
    Activations Density 0.022%

    No Known Activations