© 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. 129485
    Prev
    Next
    INDEX
    Explanations

    appropriateness, possibility, necessity

    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
     if
    -0.07
    If
    -0.07
     žád
    -0.07
     that
    -0.06
     यदि
    -0.06
     अगर
    -0.06
    ูก
    -0.06
     varsa
    -0.06
     있다면
    -0.05
     Ô
    -0.05
    POSITIVE LOGITS
     அதை
    0.07
    付出
    0.07
    将其
    0.07
    该
    0.07
     großen
    0.06
     அவர்களை
    0.06
     ಅದರ
    0.06
    iputi
    0.06
     trebuie
    0.06
     trouble
    0.06
    Activations Density 0.003%

    No Known Activations