© 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. 120436
    Prev
    Next
    INDEX
    Explanations

    cardinal directions

    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
     vaak
    -0.06
    Creating
    -0.06
     keep
    -0.06
     souvent
    -0.06
    Making
    -0.06
    MeshData
    -0.06
    oxidase
    -0.06
     reside
    -0.05
    dominated
    -0.05
    వ్య
    -0.05
    POSITIVE LOGITS
    శ్
    0.06
     सहित
    0.06
    rural
    0.06
    晴
    0.06
     cualquiera
    0.06
     deton
    0.06
     та
    0.06
     tables
    0.06
     тому
    0.05
    ेक
    0.05
    Activations Density 0.002%

    No Known Activations