© 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. 117049
    Prev
    Next
    INDEX
    Explanations

    chemokines, dihydro, be isolated

    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
    之间的
    -0.06
    之间
    -0.06
     라고
    -0.06
     believable
    -0.06
     specified
    -0.06
     .....
    -0.05
    +/-
    -0.05
     zwischen
    -0.05
     between
    -0.05
     Bupati
    -0.05
    POSITIVE LOGITS
     проєкту
    0.08
     পাঁচ
    0.07
     проє
    0.07
    ସ
    0.06
     الأخرى
    0.06
     biri
    0.06
     알아보
    0.06
     beş
    0.06
     nonprofits
    0.06
    永
    0.06
    Activations Density 0.014%

    No Known Activations