© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130026
    Prev
    Next
    INDEX
    Explanations

    dates, ranges, or selections

    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
     corrections
    -0.06
     aids
    -0.06
     bergantung
    -0.06
     സഹായി
    -0.06
     inept
    -0.06
    等の
    -0.05
     machining
    -0.05
     superst
    -0.05
     связанных
    -0.05
     awaits
    -0.05
    POSITIVE LOGITS
    两人
    0.07
    tnie
    0.06
     Holiday
    0.06
    兩人
    0.06
    酴
    0.06
    eduanya
    0.06
     Sublime
    0.06
     percor
    0.06
     Canyon
    0.06
     rosé
    0.06
    Activations Density 0.001%

    No Known Activations