© 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. 129589
    Prev
    Next
    INDEX
    Explanations

    I followed by verb

    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
     therefore
    -0.06
     Therefore
    -0.06
    therefore
    -0.06
     LENGTH
    -0.06
     by
    -0.06
    と同様
    -0.06
     굉장
    -0.06
     건축
    -0.06
     viszont
    -0.05
    👹
    -0.05
    POSITIVE LOGITS
    적인
    0.06
     miteinander
    0.06
     dapat
    0.06
    บรร
    0.06
    membership
    0.06
    렇게
    0.05
    시면
    0.05
    rí
    0.05
     variety
    0.05
    рения
    0.05
    Activations Density 0.010%

    No Known Activations