© 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. 117576
    Prev
    Next
    INDEX
    Explanations

    optional types and qualifications

    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
    句话
    -0.07
     Namun
    -0.07
    未使用
    -0.07
    UNRELATED
    -0.07
     但是
    -0.07
    此外
    -0.06
     viewpoints
    -0.06
     diferente
    -0.06
     display
    -0.06
    మ్యాచ్
    -0.06
    POSITIVE LOGITS
    Would
    0.07
     to
    0.06
     would
    0.06
    From
    0.06
    Finn
    0.06
     avrebbe
    0.06
     in
    0.06
    Where
    0.06
     lựa
    0.05
    English
    0.05
    Activations Density 0.002%

    No Known Activations