© 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. 116338
    Prev
    Next
    INDEX
    Explanations

    license or also

    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
    normally
    -0.06
    从未
    -0.06
    Alles
    -0.06
    ミ
    -0.06
     baina
    -0.06
     infrequent
    -0.06
     cerca
    -0.06
     culto
    -0.06
    从来
    -0.05
     kabhi
    -0.05
    POSITIVE LOGITS
     también
    0.08
     également
    0.08
     also
    0.08
     também
    0.08
     También
    0.07
     auch
    0.07
     Also
    0.07
     επίσης
    0.07
     또는
    0.07
     также
    0.07
    Activations Density 0.002%

    No Known Activations