© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 120716
    Prev
    Next
    INDEX
    Explanations

    institute of science departments

    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
     molti
    -0.06
     practised
    -0.06
     योग
    -0.06
     الكثير
    -0.06
     noticeable
    -0.06
    urer
    -0.06
    amazing
    -0.06
    gnię
    -0.06
    หลากหลาย
    -0.06
     amazing
    -0.06
    POSITIVE LOGITS
     uniqueness
    0.06
    ከላከ
    0.06
     Sheep
    0.05
    )=(
    0.05
    ontas
    0.05
     filly
    0.05
     relocated
    0.05
    년
    0.05
     เตรียม
    0.05
    exual
    0.05
    Activations Density 0.004%

    No Known Activations