© 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. 120338
    Prev
    Next
    INDEX
    Explanations

    citations

    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
    чної
    -0.06
     ostensibly
    -0.06
     folgender
    -0.06
    idoarjo
    -0.06
    的前提
    -0.06
    ிகளைக்
    -0.06
     najbol
    -0.06
     비슷한
    -0.06
     theses
    -0.05
    ;.
    -0.05
    POSITIVE LOGITS
     אם
    0.07
     activ
    0.06
    带着
    0.06
    が
    0.05
    但是
    0.05
     finally
    0.05
    代目
    0.05
    ם
    0.05
     แม
    0.05
     לא
    0.05
    Activations Density 0.004%

    No Known Activations