© 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. 116502
    Prev
    Next
    INDEX
    Explanations

    numbers like 4 and following want to

    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
    Imputted
    -0.15
    𒁎
    -0.15
     gacchatiti
    -0.15
    𒋝
    -0.15
    𒊦
    -0.15
     চিতের
    -0.15
    𒃡
    -0.15
    𒄆
    -0.15
    𒍍
    -0.15
    iotsit
    -0.15
    POSITIVE LOGITS
    ↵
    0.07
    )
    0.05
    不
    0.05
    etc
    0.05
    considered
    0.05
    during
    0.05
     LOSS
    0.05
    casted
    0.05
    😅
    0.05
    ದಾರ
    0.05
    Activations Density 0.003%

    No Known Activations