© 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. 117117
    Prev
    Next
    INDEX
    Explanations

    Intervenors or corporations

    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
     continúa
    -0.08
     continues
    -0.07
    continues
    -0.07
    延续
    -0.06
     ادامه
    -0.06
    发现
    -0.06
    が変わ
    -0.06
     continue
    -0.06
    到现在
    -0.06
     tiếp
    -0.06
    POSITIVE LOGITS
     prywat
    0.06
     вклад
    0.06
     thumbnail
    0.06
     hvis
    0.06
     emerging
    0.05
     which
    0.05
    と考えて
    0.05
    affected
    0.05
    requent
    0.05
    below
    0.05
    Activations Density 0.006%

    No Known Activations