© 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. 120431
    Prev
    Next
    INDEX
    Explanations

    Update, Follow, Net

    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
     intentar
    -0.07
    時間を
    -0.07
     inizia
    -0.06
     появляются
    -0.06
    留下
    -0.06
     intimated
    -0.06
     под
    -0.06
     часто
    -0.06
    Sistema
    -0.06
    ısının
    -0.06
    POSITIVE LOGITS
     उल्लेखनीय
    0.06
     ebenfalls
    0.06
     πολλ
    0.06
     Unlike
    0.06
    amless
    0.06
     επίσης
    0.06
     Conventional
    0.06
     deficiencies
    0.06
     puzzling
    0.06
    Also
    0.05
    Activations Density 0.001%

    No Known Activations