© 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. 117356
    Prev
    Next
    INDEX
    Explanations

    social process

    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
     extraordinarily
    -0.07
     ridiculously
    -0.07
     exceedingly
    -0.06
     exceptionally
    -0.06
    今の
    -0.06
     extremely
    -0.06
     prodigious
    -0.06
     superbly
    -0.06
     cones
    -0.06
     rudimentary
    -0.06
    POSITIVE LOGITS
     таком
    0.07
     such
    0.07
     against
    0.06
     dieser
    0.06
     blemishes
    0.06
     Reakt
    0.06
     μας
    0.06
     gegenüber
    0.06
    INST
    0.06
     compless
    0.06
    Activations Density 0.001%

    No Known Activations