© 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. 128991
    Prev
    Next
    INDEX
    Explanations

    national park exploration

    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
     который
    -0.06
    Elig
    -0.06
    lists
    -0.06
     knob
    -0.06
     what
    -0.06
     porous
    -0.06
     personalidade
    -0.06
     shrewd
    -0.06
    物が
    -0.06
     சாலை
    -0.06
    POSITIVE LOGITS
    Exploring
    0.06
     downstream
    0.06
     Exploration
    0.06
     outbound
    0.06
     separate
    0.06
    下游
    0.06
     daughter
    0.06
    別の
    0.06
     Tochter
    0.06
     explored
    0.06
    Activations Density 0.005%

    No Known Activations