© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 129926
    Prev
    Next
    INDEX
    Explanations

    I am unable to provide an explanation as the `MAX_ACTIVATING_TOKENS` list is empty, preventing me from identifying a specific starting point or pattern

    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
     &
    -0.06
     আরেকটি
    -0.06
    Where
    -0.06
     aj
    -0.05
    ,
    -0.05
    Right
    -0.05
    UA
    -0.05
     altro
    -0.05
     ďal
    -0.05
    Ã
    -0.05
    POSITIVE LOGITS
    筥
    0.07
     özellikle
    0.07
    aturated
    0.07
     declined
    0.07
     சாதாரண
    0.07
    ᅨ
    0.07
     lamented
    0.06
     المباراة
    0.06
     पोर्न
    0.06
     Özellikle
    0.06
    Activations Density 0.007%

    No Known Activations