© 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
    2. Gemma-4-31B
    3. 30-RES-MATRYOSHKA-131K
    4. 120331
    Prev
    Next
    INDEX
    Explanations

    sorted, eukaryotic, Male, Case, Big

    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
    Obviously
    -0.08
     возможность
    -0.07
     Obviously
    -0.07
     ৮
    -0.07
     მათი
    -0.07
     dość
    -0.06
     deras
    -0.06
     انها
    -0.06
     небольшой
    -0.06
     почина
    -0.06
    POSITIVE LOGITS
     wet
    0.07
    جان
    0.06
     भो
    0.06
    bn
    0.05
    onn
    0.05
    ildo
    0.05
     objectives
    0.05
    perfect
    0.05
    لت
    0.05
     Akademie
    0.05
    Activations Density 0.001%

    No Known Activations