© 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. 120134
    Prev
    Next
    INDEX
    Explanations

    quantities and prices

    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
     obses
    -0.07
    .|
    -0.06
    谑
    -0.06
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    -0.06
    வைத்து
    -0.06
    ↵↵↵↵↵↵↵↵↵↵
    -0.06
    ↵↵↵↵↵↵↵↵↵↵↵↵
    -0.05
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    -0.05
    На
    -0.05
    η
    -0.05
    POSITIVE LOGITS
    颓
    0.07
    DBGPRINT
    0.06
    一身
    0.06
     kinds
    0.06
     chest
    0.06
     душа
    0.06
     emotional
    0.06
     any
    0.06
    頹
    0.06
     body
    0.06
    Activations Density 0.001%

    No Known Activations