© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130733
    Prev
    Next
    INDEX
    Explanations

    leaderboard, scores, time trials

    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
     Außerdem
    -0.07
     eikä
    -0.06
     мәкалә
    -0.06
    bezpie
    -0.06
     समज
    -0.06
    kwargs
    -0.05
     properly
    -0.05
     logistical
    -0.05
    让他们
    -0.05
     الاسئله
    -0.05
    POSITIVE LOGITS
    KindOf
    0.07
     সংগ্রহের
    0.07
     различных
    0.07
    的历史
    0.07
     within
    0.06
     continually
    0.06
     hasonló
    0.06
    ɧ
    0.06
    COVER
    0.06
     새로운
    0.06
    Activations Density 0.005%

    No Known Activations