© 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. 129379
    Prev
    Next
    INDEX
    Explanations

    locations following "to" or listing places

    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
     había
    -0.07
     avait
    -0.07
    是我们
    -0.06
    avait
    -0.06
     Sauna
    -0.06
    CHANG
    -0.06
    ümüz
    -0.06
    他にも
    -0.06
     havde
    -0.06
     Change
    -0.06
    POSITIVE LOGITS
     slightly
    0.07
     कोणत्याही
    0.07
     If
    0.06
     Slightly
    0.06
    slightly
    0.06
     OK
    0.06
     кін
    0.06
     अगदी
    0.06
    任何
    0.06
     betreff
    0.06
    Activations Density 0.022%

    No Known Activations