© 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. 128804
    Prev
    Next
    INDEX
    Explanations

    official directions

    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
     but
    -0.07
     aimed
    -0.06
     so
    -0.06
    魅
    -0.06
     исклю
    -0.06
     Involved
    -0.06
     dwie
    -0.06
    遭
    -0.06
    傻
    -0.06
     exclusivos
    -0.06
    POSITIVE LOGITS
     egyéb
    0.06
    当时的
    0.06
    或其他
    0.06
     Coatings
    0.06
     কিলোমিটার
    0.06
     até
    0.06
     午
    0.06
     سپس
    0.06
    ชม
    0.06
     Cath
    0.06
    Activations Density 0.002%

    No Known Activations