© 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. 117520
    Prev
    Next
    INDEX
    Explanations

    its / his / relating

    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
     이게
    -0.07
     sadece
    -0.07
     from
    -0.07
     Ayrıca
    -0.07
     mye
    -0.07
    玤
    -0.06
    !...
    -0.06
    としている
    -0.06
    珼
    -0.06
     motores
    -0.06
    POSITIVE LOGITS
     его
    0.07
     त्याच्या
    0.07
     njegov
    0.06
     jego
    0.06
     jeho
    0.06
    Its
    0.06
     связь
    0.06
    នាំ
    0.06
     relating
    0.06
     لأنه
    0.06
    Activations Density 0.130%

    No Known Activations