© 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. 120627
    Prev
    Next
    INDEX
    Explanations

    class definitions

    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
     beachfront
    -0.07
     necessary
    -0.07
     transitory
    -0.07
    ίες
    -0.06
     homogenous
    -0.06
    调度
    -0.06
     like
    -0.06
     அவர்
    -0.06
     derzeit
    -0.06
    atory
    -0.06
    POSITIVE LOGITS
     또는
    0.06
     inay
    0.06
     could
    0.06
    ParamNum
    0.06
    JJ
    0.06
    または
    0.05
     partially
    0.05
     गर्भावस्था
    0.05
    зим
    0.05
    possibly
    0.05
    Activations Density 0.004%

    No Known Activations