© 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. 120383
    Prev
    Next
    INDEX
    Explanations

    code comments or directives

    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
     generali
    -0.07
     große
    -0.06
     городской
    -0.06
     grote
    -0.06
     family
    -0.06
     oficiales
    -0.06
     generales
    -0.06
     గురించి
    -0.06
     immaculate
    -0.06
     abbastanza
    -0.06
    POSITIVE LOGITS
    とはいえ
    0.07
     seroton
    0.06
    她的
    0.06
     meatballs
    0.06
    她是
    0.06
    れる
    0.06
    Take
    0.06
     seulement
    0.06
    Using
    0.06
    NaHCO
    0.06
    Activations Density 0.001%

    No Known Activations