© 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. 129150
    Prev
    Next
    INDEX
    Explanations

    DSP or, Enhancement, LME

    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
     neue
    -0.06
     phosphate
    -0.06
    テーブル
    -0.06
     yeni
    -0.06
    isor
    -0.06
    传输
    -0.06
     sans
    -0.06
     वॉलेट
    -0.06
    发挥
    -0.06
     புதிய
    -0.06
    POSITIVE LOGITS
    द्
    0.07
     consta
    0.06
     beschikbaar
    0.06
     música
    0.06
     boast
    0.06
     Music
    0.06
     music
    0.06
     kunnen
    0.06
     Regularly
    0.06
     clauses
    0.05
    Activations Density 0.002%

    No Known Activations