© 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. 119931
    Prev
    Next
    INDEX
    Explanations

    FirstLight

    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
     পাচ্ছে
    -0.07
     has
    -0.07
     của
    -0.07
    各式
    -0.06
     would
    -0.06
     différent
    -0.06
     після
    -0.06
     иногда
    -0.06
    有时候
    -0.06
     तमाम
    -0.06
    POSITIVE LOGITS
     ...,
    0.06
     …,
    0.06
     گرفتن
    0.06
     aquelas
    0.05
     Tarantino
    0.05
     hostility
    0.05
    ldi
    0.05
     тот
    0.05
     weighted
    0.05
    /,
    0.05
    Activations Density 0.002%

    No Known Activations