© 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. 120375
    Prev
    Next
    INDEX
    Explanations

    bereaved, grief, psychosocial, coping, traumatic

    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
    Allow
    -0.06
     permette
    -0.06
     permet
    -0.06
     мощ
    -0.06
     تفصیل
    -0.06
     χρησιμοποι
    -0.06
     চিঠ
    -0.06
     StringBuffer
    -0.06
     رفته
    -0.06
     λί
    -0.06
    POSITIVE LOGITS
    ց
    0.07
    各有
    0.06
     psycho
    0.06
    боры
    0.06
     உள
    0.06
    victim
    0.06
     psih
    0.06
     expatri
    0.06
     victim
    0.06
     তত্ত্ব
    0.05
    Activations Density 0.112%

    No Known Activations