© 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. 128665
    Prev
    Next
    INDEX
    Explanations

    Q:

    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
    常规
    -0.07
    enough
    -0.07
     Reven
    -0.07
    现在的
    -0.07
    žev
    -0.06
     necessários
    -0.06
     necesarios
    -0.06
     current
    -0.06
    मॉन
    -0.06
    estimate
    -0.06
    POSITIVE LOGITS
    !!!!!!!!!!!!!!!!
    0.07
    !!!!!!!!
    0.07
    فعيل
    0.06
     पहली
    0.06
     INSPIRE
    0.06
     PSOE
    0.06
    xxxxxxxx
    0.06
    ી
    0.06
     !!!!!
    0.06
    ometri
    0.05
    Activations Density 0.001%

    No Known Activations